Dong Wang, Simon King, Nick Evans, and Raphael Troncy. Direct posterior confidence for out-of-vocabulary spoken term detection. In Proc. ACM Multimedia 2010 Searching Spontaneous Conversational Speech Workshop, October 2010. [ bib | DOI | .pdf ]
Spoken term detection (STD) is a fundamental task in spoken information retrieval. Compared to conventional speech transcription and keyword spotting, STD is an open-vocabulary task and is necessarily required to address out-of-vocabulary (OOV) terms. Approaches based on subword units, e.g. phonemes, are widely used to solve the OOV issue; however, performance on OOV terms is still significantly inferior to that for in-vocabulary (INV) terms. The performance degradation on OOV terms can be attributed to a multitude of factors. A particular factor we address in this paper is that the acoustic and language models used for speech transcribing are highly vulnerable to OOV terms, which leads to unreliable confidence measures and error-prone detections. A direct posterior confidence measure that is derived from discriminative models has been proposed for STD. In this paper, we utilize this technique to tackle the weakness of OOV terms in confidence estimation. Neither acoustic models nor language models being included in the computation, the new confidence avoids the weak modeling problem with OOV terms. Our experiments, set up on multi-party meeting speech which is highly spontaneous and conversational, demonstrate that the proposed technique improves STD performance on OOV terms significantly; when combined with conventional lattice-based confidence, a significant improvement in performance is obtained on both INVs and OOVs. Furthermore, the new confidence measure technique can be combined together with other advanced techniques for OOV treatment, such as stochastic pronunciation modeling and term-dependent confidence discrimination, which leads to an integrated solution for OOV STD with greatly improved performance.
Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi. An analysis of HMM-based prediction of articulatory movements. Speech Communication, 52(10):834-846, October 2010. [ bib | DOI ]
This paper presents an investigation into predicting the movement of a speaker's mouth from text input using hidden Markov models (HMM). A corpus of human articulatory movements, recorded by electromagnetic articulography (EMA), is used to train HMMs. To predict articulatory movements for input text, a suitable model sequence is selected and a maximum-likelihood parameter generation (MLPG) algorithm is used to generate output articulatory trajectories. Unified acoustic-articulatory HMMs are introduced to integrate acoustic features when an acoustic signal is also provided with the input text. Several aspects of this method are analyzed in this paper, including the effectiveness of context-dependent modeling, the role of supplementary acoustic input, and the appropriateness of certain model structures for the unified acoustic-articulatory models. When text is the sole input, we find that fully context-dependent models significantly outperform monophone and quinphone models, achieving an average root mean square (RMS) error of 1.945 mm and an average correlation coefficient of 0.600. When both text and acoustic features are given as input to the system, the difference between the performance of quinphone models and fully context-dependent models is no longer significant. The best performance overall is achieved using unified acoustic-articulatory quinphone HMMs with separate clustering of acoustic and articulatory model parameters, a synchronous-state sequence, and a dependent-feature model structure, with an RMS error of 0.900 mm and a correlation coefficient of 0.855 on average. Finally, we also apply the same quinphone HMMs to the acoustic-articulatory, or inversion, mapping problem, where only acoustic input is available. An average root mean square (RMS) error of 1.076 mm and an average correlation coefficient of 0.812 are achieved. Taken together, our results demonstrate how text and acoustic inputs both contribute to the prediction of articulatory movements in the method used.
Keywords: Hidden Markov model; Articulatory features; Parameter generation
Jochen Ehnes. A precise controllable projection system for projected virtual characters and its calibration. In IEEE International Symposium on Mixed and Augmented Reality 2010 Science and Technolgy Proceedings, pages 221-222, Seoul, Korea, October 2010. [ bib | .pdf ]
In this paper we describe a system to project virtual characters that shall live with us in the same environment. In order to project the characters' visual representations onto room surfaces we use a con- trollable projector.
Zhen-Hua Ling, Korin Richmond, and Junichi Yamagishi. HMM-based text-to-articulatory-movement prediction and analysis of critical articulators. In Proc. Interspeech, pages 2194-2197, Makuhari, Japan, September 2010. [ bib | .pdf ]
In this paper we present a method to predict the movement of a speaker's mouth from text input using hidden Markov models (HMM). We have used a corpus of human articulatory movements, recorded by electromagnetic articulography (EMA), to train HMMs. To predict articulatory movements from text, a suitable model sequence is selected and the maximum-likelihood parameter generation (MLPG) algorithm is used to generate output articulatory trajectories. In our experiments, we find that fully context-dependent models outperform monophone and quinphone models, achieving an average root mean square (RMS) error of 1.945mm when state durations are predicted from text, and 0.872mm when natural state durations are used. Finally, we go on to analyze the prediction error for different EMA dimensions and phone types. We find a clear pattern emerges that the movements of so-called critical articulators can be predicted more accurately than the average performance.
Keywords: Hidden Markov model, articulatory features, parameter generation, critical articulators
Daniel Felps, Christian Geng, Michael Berger, Korin Richmond, and Ricardo Gutierrez-Osuna. Relying on critical articulators to estimate vocal tract spectra in an articulatory-acoustic database. In Proc. Interspeech, pages 1990-1993, September 2010. [ bib | .pdf ]
We present a new phone-dependent feature weighting scheme that can be used to map articulatory configurations (e.g. EMA) onto vocal tract spectra (e.g. MFCC) through table lookup. The approach consists of assigning feature weights according to a feature's ability to predict the acoustic distance between frames. Since an articulator's predictive accuracy is phone-dependent (e.g., lip location is a better predictor for bilabial sounds than for palatal sounds), a unique weight vector is found for each phone. Inspection of the weights reveals a correspondence with the expected critical articulators for many phones. The proposed method reduces overall cepstral error by 6% when compared to a uniform weighting scheme. Vowels show the greatest benefit, though improvements occur for 80% of the tested phones.
Keywords: speech production, speech synthesis
Korin Richmond, Robert Clark, and Sue Fitt. On generating Combilex pronunciations via morphological analysis. In Proc. Interspeech, pages 1974-1977, Makuhari, Japan, September 2010. [ bib | .pdf ]
Combilex is a high-quality lexicon that has been developed specifically for speech technology purposes and recently released by CSTR. Combilex benefits from many advanced features. This paper explores one of these: the ability to generate fully-specified transcriptions for morphologically derived words automatically. This functionality was originally implemented to encode the pronunciations of derived words in terms of their constituent morphemes, thus accelerating lexicon development and ensuring a high level of consistency. In this paper, we propose this method of modelling pronunciations can be exploited further by combining it with a morphological parser, thus yielding a method to generate full transcriptions for unknown derived words. Not only could this accelerate adding new derived words to Combilex, but it could also serve as an alternative to conventional letter-to-sound rules. This paper presents preliminary work indicating this is a promising direction.
Keywords: combilex lexicon, letter-to-sound rules, grapheme-to-phoneme conversion, morphological decomposition
Yong Guan, Jilei Tian, Yi-Jian Wu, Junichi Yamagishi, and Jani Nurminen. A unified and automatic approach of Mandarin HTS system. In Proc. SSW7, Kyoto, Japan, September 2010. [ bib | .pdf ]
Keywords: HTS, speech synthesis, mandarin
Mirjam Wester. Cross-lingual talker discrimination. In Proc. Interspeech, Makuhari, Japan, September 2010. [ bib | .pdf ]
This paper describes a talker discrimination experiment in which native English listeners were presented with two sentences spoken by bilingual talkers (English/German and English/Finnish) and were asked to judge whether they thought the sentences were spoken by the same person or not. Equal amounts of cross-lingual and matched-language trials were presented. The experiments showed that listeners are able to complete this task well, they can discriminate between talkers significantly better than chance. However, listeners are significantly less accurate on cross-lingual talker trials than on matched-language pairs. No significant differences were found on this task between German and Finnish. Bias (B”) and Sensitivity (A') values are presented to analyse the listeners' behaviour in more detail. The results are promising for the evaluation of EMIME, a project covering speech-to-speech translation with speaker adaptation.
João Cabral, Steve Renals, Korin Richmond, and Junichi Yamagishi. Transforming voice source parameters in a HMM-based speech synthesiser with glottal post-filtering. In Proc. 7th ISCA Speech Synthesis Workshop (SSW7), pages 365-370, NICT/ATR, Kyoto, Japan, September 2010. [ bib | .pdf ]
Control over voice quality, e.g. breathy and tense voice, is important for speech synthesis applications. For example, transformations can be used to modify aspects of the voice re- lated to speaker's identity and to improve expressiveness. How- ever, it is hard to modify voice characteristics of the synthetic speech, without degrading speech quality. State-of-the-art sta- tistical speech synthesisers, in particular, do not typically al- low control over parameters of the glottal source, which are strongly correlated with voice quality. Consequently, the con- trol of voice characteristics in these systems is limited. In con- trast, the HMM-based speech synthesiser proposed in this paper uses an acoustic glottal source model. The system passes the glottal signal through a whitening filter to obtain the excitation of voiced sounds. This technique, called glottal post-filtering, allows to transform voice characteristics of the synthetic speech by modifying the source model parameters. We evaluated the proposed synthesiser in a perceptual ex- periment, in terms of speech naturalness, intelligibility, and similarity to the original speaker's voice. The results show that it performed as well as a HMM-based synthesiser, which generates the speech signal with a commonly used high-quality speech vocoder.
Keywords: HMM-based speech synthesis, voice quality, glottal post-filter
Ravi Chander Vipperla, Steve Renals, and Joe Frankel. Augmentation of adaptation data. In Proc. Interspeech, pages 530-533, Makuhari, Japan, September 2010. [ bib | .pdf ]
Linear regression based speaker adaptation approaches can improve Automatic Speech Recognition (ASR) accuracy significantly for a target speaker. However, when the available adaptation data is limited to a few seconds, the accuracy of the speaker adapted models is often worse compared with speaker independent models. In this paper, we propose an approach to select a set of reference speakers acoustically close to the target speaker whose data can be used to augment the adaptation data. To determine the acoustic similarity of two speakers, we propose a distance metric based on transforming sample points in the acoustic space with the regression matrices of the two speakers. We show the validity of this approach through a speaker identification task. ASR results on SCOTUS and AMI corpora with limited adaptation data of 10 to 15 seconds augmented by data from selected reference speakers show a significant improvement in Word Error Rate over speaker independent and speaker adapted models.
Dong Wang, Simon King, Nick Evans, and Raphael Troncy. CRF-based stochastic pronunciation modelling for out-of-vocabulary spoken term detection. In Proc. Interspeech, Makuhari, Chiba, Japan, September 2010. [ bib ]
Out-of-vocabulary (OOV) terms present a significant challenge to spoken term detection (STD). This challenge, to a large extent, lies in the high degree of uncertainty in pronunciations of OOV terms. In previous work, we presented a stochastic pronunciation modeling (SPM) approach to compensate for this uncertainty. A shortcoming of our original work, however, is that the SPM was based on a joint-multigram model (JMM), which is suboptimal. In this paper, we propose to use conditional random fields (CRFs) for letter-to-sound conversion, which significantly improves quality of the predicted pronunciations. When applied to OOV STD, we achieve consider- able performance improvement with both a 1-best system and an SPM-based system.
Oliver Watts, Junichi Yamagishi, and Simon King. The role of higher-level linguistic features in HMM-based speech synthesis. In Proc. Interspeech, pages 841-844, Makuhari, Japan, September 2010. [ bib | .pdf ]
We analyse the contribution of higher-level elements of the linguistic specification of a data-driven speech synthesiser to the naturalness of the synthetic speech which it generates. The system is trained using various subsets of the full feature-set, in which features relating to syntactic category, intonational phrase boundary, pitch accent and boundary tones are selectively removed. Utterances synthesised by the different configurations of the system are then compared in a subjective evaluation of their naturalness. The work presented forms background analysis for an ongoing set of experiments in performing text-to-speech (TTS) conversion based on shallow features: features that can be trivially extracted from text. By building a range of systems, each assuming the availability of a different level of linguistic annotation, we obtain benchmarks for our on-going work.
Gregor Hofer and Korin Richmond. Comparison of HMM and TMDN methods for lip synchronisation. In Proc. Interspeech, pages 454-457, Makuhari, Japan, September 2010. [ bib | .pdf ]
This paper presents a comparison between a hidden Markov model (HMM) based method and a novel artificial neural network (ANN) based method for lip synchronisation. Both model types were trained on motion tracking data, and a perceptual evaluation was carried out comparing the output of the models, both to each other and to the original tracked data. It was found that the ANN-based method was judged significantly better than the HMM based method. Furthermore, the original data was not judged significantly better than the output of the ANN method.
Keywords: hidden Markov model (HMM), mixture density network, lip synchronisation, inversion mapping
Junichi Yamagishi, Oliver Watts, Simon King, and Bela Usabaev. Roles of the average voice in speaker-adaptive HMM-based speech synthesis. In Proc. Interspeech, pages 418-421, Makuhari, Japan, September 2010. [ bib | .pdf ]
In speaker-adaptive HMM-based speech synthesis, there are typically a few speakers for which the output synthetic speech sounds worse than that of other speakers, despite having the same amount of adaptation data from within the same corpus. This paper investigates these fluctuations in quality and concludes that as mel-cepstral distance from the average voice becomes larger, the MOS naturalness scores generally become worse. Although this negative correlation is not that strong, it suggests a way to improve the training and adaptation strategies. We also draw comparisons between our findings and the work of other researchers regarding “vocal attractiveness.”
Keywords: speech synthesis, HMM, average voice, speaker adaptation
Mirjam Wester, John Dines, Matthew Gibson, Hui Liang, Yi-Jian Wu, Lakshmi Saheer, Simon King, Keiichiro Oura, Philip N. Garner, William Byrne, Yong Guan, Teemu Hirsimäki, Reima Karhila, Mikko Kurimo, Matt Shannon, Sayaka Shiota, Jilei Tian, Keiichi Tokuda, and Junichi Yamagishi. Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project. In Proc. 7th ISCA Speech Synthesis Workshop, Kyoto, Japan, September 2010. [ bib | .pdf ]
This paper provides an overview of speaker adaptation research carried out in the EMIME speech-to-speech translation (S2ST) project. We focus on how speaker adaptation transforms can be learned from speech in one language and applied to the acoustic models of another language. The adaptation is transferred across languages and/or from recognition models to synthesis models. The various approaches investigated can all be viewed as a process in which a mapping is defined in terms of either acoustic model states or linguistic units. The mapping is used to transfer either speech data or adaptation transforms between the two models. Because the success of speaker adaptation in text-to-speech synthesis is measured by judging speaker similarity, we also discuss issues concerning evaluation of speaker similarity in an S2ST scenario.
Michael Pucher, Dietmar Schabus, and Junichi Yamagishi. Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners. In Proc. Interspeech, pages 2186-2189, Makuhari, Japan, September 2010. [ bib | .pdf ]
In this paper we evaluate a method for generating synthetic speech at high speaking rates based on the interpolation of hidden semi-Markov models (HSMMs) trained on speech data recorded at normal and fast speaking rates. The subjective evaluation was carried out with both blind listeners, who are used to very fast speaking rates, and sighted listeners. We show that we can achieve a better intelligibility rate and higher voice quality with this method compared to standard HSMM-based duration modeling. We also evaluate duration modeling with the interpolation of all the acoustic features including not only duration but also spectral and F0 models. An analysis of the mean squared error (MSE) of standard HSMM-based duration modeling for fast speech identifies problematic linguistic contexts for duration modeling.
Keywords: speech synthesis, fast speech, hidden semi- Markov model
Sebastian Andersson, Junichi Yamagishi, and Robert Clark. Utilising spontaneous conversational speech in HMM-based speech synthesis. In The 7th ISCA Tutorial and Research Workshop on Speech Synthesis, September 2010. [ bib | .pdf ]
Spontaneous conversational speech has many characteristics that are currently not well modelled in unit selection and HMM-based speech synthesis. But in order to build synthetic voices more suitable for interaction we need data that exhibits more conversational characteristics than the generally used read aloud sentences. In this paper we will show how carefully selected utterances from a spontaneous conversation was instrumental for building an HMM-based synthetic voices with more natural sounding conversational characteristics than a voice based on carefully read aloud sentences. We also investigated a style blending technique as a solution to the inherent problem of phonetic coverage in spontaneous speech data. But the lack of an appropriate representation of spontaneous speech phenomena probably contributed to results showing that we could not yet compete with the speech quality achieved for grammatical sentences.
Javier Tejedor, Doroteo T. Toledano, Miguel Bautista, Simon King, Dong Wang, and Jose Colas. Augmented set of features for confidence estimation in spoken term detection. In Proc. Interspeech, September 2010. [ bib | .pdf ]
Discriminative confidence estimation along with confidence normalisation have been shown to construct robust decision maker modules in spoken term detection (STD) systems. Discriminative confidence estimation, making use of termdependent features, has been shown to improve the widely used lattice-based confidence estimation in STD. In this work, we augment the set of these term-dependent features and show a significant improvement in the STD performance both in terms of ATWV and DET curves in experiments conducted on a Spanish geographical corpus. This work also proposes a multiple linear regression analysis to carry out the feature selection. Next, the most informative features derived from it are used within the discriminative confidence on the STD system.
Oliver Watts, Junichi Yamagishi, and Simon King. Letter-based speech synthesis. In Proc. Speech Synthesis Workshop 2010, pages 317-322, Nara, Japan, September 2010. [ bib | .pdf ]
Initial attempts at performing text-to-speech conversion based on standard orthographic units are presented, forming part of a larger scheme of training TTS systems on features that can be trivially extracted from text. We evaluate the possibility of using the technique of decision-tree-based context clustering conventionally used in HMM-based systems for parametertying to handle letter-to-sound conversion. We present the application of a method of compound-feature discovery to corpusbased speech synthesis. Finally, an evaluation of intelligibility of letter-based systems and more conventional phoneme-based systems is presented.
Atef Ben Youssef, Pierre Badin, and Gérard Bailly. Can tongue be recovered from face? the answer of data-driven statistical models. In Proc. Interspeech, pages 2002-2005, Makuhari, Japan, September 2010. [ bib | .pdf ]
This study revisits the face-to-tongue articulatory inversion problem in speech. We compare the Multi Linear Regression method (MLR) with two more sophisticated methods based on Hidden Markov Models (HMMs) and Gaussian Mixture Models (GMMs), using the same French corpus of articulatory data acquired by ElectroMagnetoGraphy. GMMs give overall results better than HMMs, but MLR does poorly. GMMs and HMMs maintain the original phonetic class distribution, though with some centralisation effects, effects still much stronger with MLR. A detailed analysis shows that, if the jaw / lips / tongue tip synergy helps recovering front high vowels and coronal consonants, the velars are not recovered at all. It is therefore not possible to recover reliably tongue from face
O. Watts, J. Yamagishi, S. King, and K. Berkling. Synthesis of child speech with HMM adaptation and voice conversion. Audio, Speech, and Language Processing, IEEE Transactions on, 18(5):1005-1016, July 2010. [ bib | DOI | .pdf ]
The synthesis of child speech presents challenges both in the collection of data and in the building of a synthesizer from that data. We chose to build a statistical parametric synthesizer using the hidden Markov model (HMM)-based system HTS, as this technique has previously been shown to perform well for limited amounts of data, and for data collected under imperfect conditions. Six different configurations of the synthesizer were compared, using both speaker-dependent and speaker-adaptive modeling techniques, and using varying amounts of data. For comparison with HMM adaptation, techniques from voice conversion were used to transform existing synthesizers to the characteristics of the target speaker. Speaker-adaptive voices generally outperformed child speaker-dependent voices in the evaluation. HMM adaptation outperformed voice conversion style techniques when using the full target speaker corpus; with fewer adaptation data, however, no significant listener preference for either HMM adaptation or voice conversion methods was found.
Keywords: HMM adaptation techniques;child speech synthesis;hidden Markov model;speaker adaptive modeling technique;speaker dependent technique;speaker-adaptive voice;statistical parametric synthesizer;target speaker corpus;voice conversion;hidden Markov models;speech synthesis;
Alice Turk, James Scobbie, Christian Geng, Barry Campbell, Catherine Dickie, Eddie Dubourg, Ellen Gurman Bard, William Hardcastle, Mariam Hartinger, Simon King, Robin Lickley, Cedric Macmartin, Satsuki Nakai, Steve Renals, Korin Richmond, Sonja Schaeffler, Kevin White, Ronny Wiegand, and Alan Wrench. An Edinburgh speech production facility. Poster presented at the 12th Conference on Laboratory Phonology, Albuquerque, New Mexico., July 2010. [ bib | .pdf ]
D. Wang, S. King, and J. Frankel. Stochastic pronunciation modelling for out-of-vocabulary spoken term detection. Audio, Speech, and Language Processing, IEEE Transactions on, PP(99), July 2010. [ bib | DOI ]
Spoken term detection (STD) is the name given to the task of searching large amounts of audio for occurrences of spoken terms, which are typically single words or short phrases. One reason that STD is a hard task is that search terms tend to contain a disproportionate number of out-of-vocabulary (OOV) words. The most common approach to STD uses subword units. This, in conjunction with some method for predicting pronunciations of OOVs from their written form, enables the detection of OOV terms but performance is considerably worse than for in-vocabulary terms. This performance differential can be largely attributed to the special properties of OOVs. One such property is the high degree of uncertainty in the pronunciation of OOVs. We present a stochastic pronunciation model (SPM) which explicitly deals with this uncertainty. The key insight is to search for all possible pronunciations when detecting an OOV term, explicitly capturing the uncertainty in pronunciation. This requires a probabilistic model of pronunciation, able to estimate a distribution over all possible pronunciations. We use a joint-multigram model (JMM) for this and compare the JMM-based SPM with the conventional soft match approach. Experiments using speech from the meetings domain demonstrate that the SPM performs better than soft match in most operating regions, especially at low false alarm probabilities. Furthermore, SPM and soft match are found to be complementary: their combination provides further performance gains.
Mikko Kurimo, William Byrne, John Dines, Philip N. Garner, Matthew Gibson, Yong Guan, Teemu Hirsimäki, Reima Karhila, Simon King, Hui Liang, Keiichiro Oura, Lakshmi Saheer, Matt Shannon, Sayaka Shiota, Jilei Tian, Keiichi Tokuda, Mirjam Wester, Yi-Jian Wu, and Junichi Yamagishi. Personalising speech-to-speech translation in the EMIME project. In Proc. ACL 2010 System Demonstrations, Uppsala, Sweden, July 2010. [ bib | .pdf ]
In the EMIME project we have studied unsupervised cross-lingual speaker adaptation. We have employed an HMM statistical framework for both speech recognition and synthesis which provides transformation mechanisms to adapt the synthesized voice in TTS (text-to-speech) using the recognized voice in ASR (automatic speech recognition). An important application for this research is personalised speech-to-speech translation that will use the voice of the speaker in the input language to utter the translated sentences in the output language. In mobile environments this enhances the users' interaction across language barriers by making the output speech sound more like the original speaker's way of speaking, even if she or he could not speak the output language.
J. Yamagishi, B. Usabaev, S. King, O. Watts, J. Dines, J. Tian, R. Hu, Y. Guan, K. Oura, K. Tokuda, R. Karhila, and M. Kurimo. Thousands of voices for HMM-based speech synthesis - analysis and application of TTS systems built on various ASR corpora. IEEE Transactions on Audio, Speech and Language Processing, 18(5):984-1004, July 2010. [ bib | DOI ]
In conventional speech synthesis, large amounts of phonetically balanced speech data recorded in highly controlled recording studio environments are typically required to build a voice. Although using such data is a straightforward solution for high quality synthesis, the number of voices available will always be limited, because recording costs are high. On the other hand, our recent experiments with HMM-based speech synthesis systems have demonstrated that speaker-adaptive HMM-based speech synthesis (which uses an “average voice model” plus model adaptation) is robust to non-ideal speech data that are recorded under various conditions and with varying microphones, that are not perfectly clean, and/or that lack phonetic balance. This enables us to consider building high-quality voices on “non-TTS” corpora such as ASR corpora. Since ASR corpora generally include a large number of speakers, this leads to the possibility of producing an enormous number of voices automatically. In this paper, we demonstrate the thousands of voices for HMM-based speech synthesis that we have made from several popular ASR corpora such as the Wall Street Journal (WSJ0, WSJ1, and WSJCAM0), Resource Management, Globalphone, and SPEECON databases. We also present the results of associated analysis based on perceptual evaluation, and discuss remaining issues.
Keywords: Automatic speech recognition (ASR), H Triple S (HTS), SPEECON database, WSJ database, average voice, hidden Markov model (HMM)-based speech synthesis, speaker adaptation, speech synthesis, voice conversion
Sebastian Andersson, Kallirroi Georgila, David Traum, Matthew Aylett, and Robert Clark. Prediction and realisation of conversational characteristics by utilising spontaneous speech for unit selection. In Speech Prosody 2010, May 2010. [ bib | .pdf ]
Unit selection speech synthesis has reached high levels of naturalness and intelligibility for neutral read aloud speech. However, synthetic speech generated using neutral read aloud data lacks all the attitude, intention and spontaneity associated with everyday conversations. Unit selection is heavily data dependent and thus in order to simulate human conversational speech, or create synthetic voices for believable virtual characters, we need to utilise speech data with examples of how people talk rather than how people read. In this paper we included carefully selected utterances from spontaneous conversational speech in a unit selection voice. Using this voice and by automatically predicting type and placement of lexical fillers and filled pauses we can synthesise utterances with conversational characteristics. A perceptual listening test showed that it is possible to make synthetic speech sound more conversational without degrading naturalness.
R. Barra-Chicote, J. Yamagishi, S. King, J. Manuel Monero, and J. Macias-Guarasa. Analysis of statistical parametric and unit-selection speech synthesis systems applied to emotional speech. Speech Communication, 52(5):394-404, May 2010. [ bib | DOI ]
We have applied two state-of-the-art speech synthesis techniques (unit selection and HMM-based synthesis) to the synthesis of emotional speech. A series of carefully designed perceptual tests to evaluate speech quality, emotion identification rates and emotional strength were used for the six emotions which we recorded - happiness, sadness, anger, surprise, fear, disgust. For the HMM-based method, we evaluated spectral and source components separately and identified which components contribute to which emotion. Our analysis shows that, although the HMM method produces significantly better neutral speech, the two methods produce emotional speech of similar quality, except for emotions having context-dependent prosodic patterns. Whilst synthetic speech produced using the unit selection method has better emotional strength scores than the HMM-based method, the HMM-based method has the ability to manipulate the emotional strength. For emotions that are characterized by both spectral and prosodic components, synthetic speech using unit selection methods was more accurately identified by listeners. For emotions mainly characterized by prosodic components, HMM-based synthetic speech was more accurately identified. This finding differs from previous results regarding listener judgements of speaker similarity for neutral speech. We conclude that unit selection methods require improvements to prosodic modeling and that HMM-based methods require improvements to spectral modeling for emotional speech. Certain emotions cannot be reproduced well by either method.
Keywords: Emotional speech synthesis; HMM-based synthesis; Unit selection
Atef Ben Youssef, Pierre Badin, Gérard Bailly, and Viet-Anh Tran. Méthodes basées sur les hmms et les gmms pour l'inversion acoustico-articulatoire en parole. In Proc. JEP, pages 249-252, Mons, Belgium, May 2010. [ bib | .pdf ]
Two speech inversion methods are implemented and compared. In the first, multistream Hidden Markov Models (HMMs) of phonemes are jointly trained from synchronous streams of articulatory data acquired by EMA and speech spectral parameters; an acoustic recognition system uses the acoustic part of the HMMs to deliver a phoneme chain and the states durations; this information is then used by a trajectory formation procedure based on the articulatory part of the HMMs to resynthesise the articulatory data. In the second, Gaussian Mixture Models (GMMs) are trained on these streams to associate directly articulatory frames with acoustic frames in context. Over a corpus of 17 minutes uttered by a French speaker, the RMS error was 1,66 mm with the HMMs and 2,25 mm with the GMMs.
Dong Wang, Simon King, Joe Frankel, and Peter Bell. Stochastic pronunciation modelling and soft match for out-of-vocabulary spoken term detection. In Proc. ICASSP, Dallas, Texas, USA, March 2010. [ bib | .pdf ]
A major challenge faced by a spoken term detection (STD) system is the detection of out-of-vocabulary (OOV) terms. Although a subword-based STD system is able to detect OOV terms, performance reduction is always observed compared to in-vocabulary terms. One challenge that OOV terms bring to STD is the pronunciation uncertainty. A commonly used approach to address this problem is a soft matching procedure,and the other is the stochastic pronunciation modelling (SPM) proposed by the authors. In this paper we compare these two approaches, and combine them using a discriminative decision strategy. Experimental results demonstrated that SPM and soft match are highly complementary, and their combination gives significant performance improvement to OOV term detection.
Keywords: confidence estimation, spoken term detection, speech recognition
Kallirroi Georgila, Maria Wolters, Johanna D. Moore, and Robert H. Logie. The MATCH corpus: A corpus of older and younger users' interactions with spoken dialogue systems. Language Resources and Evaluation, 44(3):221-261, March 2010. [ bib | DOI ]
We present the MATCH corpus, a unique data set of 447 dialogues in which 26 older and 24 younger adults interact with nine different spoken dialogue systems. The systems varied in the number of options presented and the confirmation strategy used. The corpus also contains information about the users' cognitive abilities and detailed usability assessments of each dialogue system. The corpus, which was collected using a Wizard-of-Oz methodology, has been fully transcribed and annotated with dialogue acts and “Information State Update” (ISU) representations of dialogue context. Dialogue act and ISU annotations were performed semi-automatically. In addition to describing the corpus collection and annotation, we present a quantitative analysis of the interaction behaviour of older and younger users and discuss further applications of the corpus. We expect that the corpus will provide a key resource for modelling older people's interaction with spoken dialogue systems.
Keywords: Spoken dialogue corpora, Spoken dialogue systems, Cognitive ageing, Annotation, Information states, Speech acts, User simulations, Speech recognition
Peter Bell. Full covariance modelling for speech recognition. PhD thesis, University of Edinburgh, 2010. [ bib | .pdf ]
HMM-based systems for Automatic Speech Recognition typically model the acoustic features using mixtures of multivariate Gaussians. In this thesis, we consider the problem of learning a suitable covariance matrix for each Gaussian. A variety of schemes have been proposed for controlling the number of covariance parameters per Gaussian, and studies have shown that in general, the greater the number of parameters used in the models, the better the recognition performance. We therefore investigate systems with full covariance Gaussians. However, in this case, the obvious choice of parameters - given by the sample covariance matrix - leads to matrices that are poorly-conditioned, and do not generalise well to unseen test data. The problem is particularly acute when the amount of training data is limited. We propose two solutions to this problem: firstly, we impose the requirement that each matrix should take the form of a Gaussian graphical model, and introduce a method for learning the parameters and the model structure simultaneously. Secondly, we explain how an alternative estimator, the shrinkage estimator, is preferable to the standard maximum likelihood estimator, and derive formulae for the optimal shrinkage intensity within the context of a Gaussian mixture model. We show how this relates to the use of a diagonal covariance smoothing prior. We compare the effectiveness of these techniques to standard methods on a phone recognition task where the quantity of training data is artificially constrained. We then investigate the performance of the shrinkage estimator on a large-vocabulary conversational telephone speech recognition task. Discriminative training techniques can be used to compensate for the invalidity of the model correctness assumption underpinning maximum likelihood estimation. On the large-vocabulary task, we use discriminative training of the full covariance models and diagonal priors to yield improved recognition performance.
Erich Zwyssig, Mike Lincoln, and Steve Renals. A digital microphone array for distant speech recognition. In Proc. IEEE ICASSP-10, pages 5106-5109, 2010. [ bib | DOI | .pdf ]
In this paper, the design, implementation and testing of a digital microphone array is presented. The array uses digital MEMS microphones which integrate the microphone, amplifier and analogue to digital converter on a single chip in place of the analogue microphones and external audio interfaces currently used. The device has the potential to be smaller, cheaper and more flexible than typical analogue arrays, however the effect on speech recognition performance of using digital microphones is as yet unknown. In order to evaluate the effect, an analogue array and the new digital array are used to simultaneously record test data for a speech recognition experiment. Initial results employing no adaptation show that performance using the digital array is significantly worse (14% absolute WER) than the analogue device. Subsequent experiments using MLLR and CMLLR channel adaptation reduce this gap, and employing MLLR for both channel and speaker adaptation reduces the difference between the arrays to 4.5% absolute WER.
Maria Wolters and Marilyn McGee-Lennon. Designing usable and acceptable reminders for the home. In Proc. AAATE Workshop AT Technology Transfer, Sheffield, UK, 2010. [ bib | .pdf ]
Electronic reminders can play a key role in enabling people to manage their care and remain independent in their own homes for longer. The MultiMemoHome project aims to develop reminder designs that are accessible and usable for users with a range of abilities and preferences. In an initial exploration of key design parameters, we surveyed 378 adults from all age groups online (N=206) and by post (N= 172). The wide spread of preferences that we found illustrates the importance of adapting reminder solutions to individuals. We present two reusable personas that emerged from the research and discuss how questionnaires can be used for technology transfer.
Steve Renals. Recognition and understanding of meetings. In Proc. NAACL/HLT, pages 1-9, 2010. [ bib | .pdf ]
This paper is about interpreting human communication in meetings using audio, video and other signals. Automatic meeting recognition and understanding is extremely challenging, since communication in a meeting is spontaneous and conversational, and involves multiple speakers and multiple modalities. This leads to a number of significant research problems in signal processing, in speech recognition, and in discourse interpretation, taking account of both individual and group behaviours. Addressing these problems requires an interdisciplinary effort. In this paper, I discuss the capture and annotation of multimodal meeting recordings - resulting in the AMI meeting corpus - and how we have built on this to develop techniques and applications for the recognition and interpretation of meetings.
Jonathan Kilgour, Jean Carletta, and Steve Renals. The Ambient Spotlight: Queryless desktop search from meeting speech. In Proc ACM Multimedia 2010 Workshop SSCS 2010, 2010. [ bib | DOI | .pdf ]
It has recently become possible to record any small meeting using a laptop equipped with a plug-and-play USB microphone array. We show the potential for such recordings in a personal aid that allows project managers to record their meetings and, when reviewing them afterwards through a standard calendar interface, to find relevant documents on their computer. This interface is intended to supplement or replace the textual searches that managers typically perform. The prototype, which relies on meeting speech recognition and topic segmentation, formulates and runs desktop search queries in order to present its results.
Michael Berger, Gregor Hofer, and Hiroshi Shimodaira. Carnival: a modular framework for automated facial animation. Poster at SIGGRAPH 2010, 2010. Bronze award winner, ACM Student Research Competition. [ bib | .pdf ]
Simon King. Speech synthesis. In Morgan and Ellis, editors, Speech and Audio Signal Processing. Wiley, 2010. [ bib ]
No abstract (this is a book chapter)
Anna C. Janska and Robert A. J. Clark. Native and non-native speaker judgements on the quality of synthesized speech. In Proc. Interspeech, pages 1121-1124, 2010. [ bib | .pdf ]
The difference between native speakers' and non-native speak- ers' naturalness judgements of synthetic speech is investigated. Similar/difference judgements are analysed via a multidimensional scaling analysis and compared to Mean opinion scores. It is shown that although the two groups generally behave in a similar manner the variance of non-native speaker judgements is generally higher. While both groups of subject can clearly distinguish natural speech from the best synthetic examples, the groups' responses to different artefacts present in the synthetic speech can vary.
M. Wester. The EMIME Bilingual Database. Technical Report EDI-INF-RR-1388, The University of Edinburgh, 2010. [ bib | .pdf ]
This paper describes the collection of a bilingual database of Finnish/English and German/English data. In addition, the accents of the talkers in the database have been rated. English, German and Finnish listeners assessed the English, German and Finnish talkersâ degree of foreign accent in English. Native English listeners showed higher inter-listener agreement than non-native listeners. Further analyses showed that non-native listeners judged Finnish and German female talkers to be significantly less accented than do English listeners. German males are judged less accented by Finnish listeners than they are by English and German listeners and there is no difference between listeners as to how they judge the accent of Finnish males. Finally, all English talkers are judged more accented by non-native listeners than they are by native English listeners.
P. L. De Leon, V. R. Apsingekar, M. Pucher, and J. Yamagishi. Revisiting the security of speaker verification systems against imposture using synthetic speech. In Proc. ICASSP 2010, Dallas, Texas, USA, 2010. [ bib | .pdf ]
Maria Wolters, Klaus-Peter Engelbrecht, Florian Gödde, Sebastian Möller, Anja Naumann, and Robert Schleicher. Making it easier for older people to talk to smart homes: Using help prompts to shape users' speech. Universal Access in the Information Society, 9(4):311-325, 2010. [ bib | DOI ]
It is well known that help prompts shape how users talk to spoken dialogue systems. This study investigated the effect of help prompt placement on older users' interaction with a smart home interface. In the dynamic help condition, help was only given in response to system errors; in the inherent help condition, it was also given at the start of each task. Fifteen older and sixteen younger users interacted with a smart home system using two different scenarios. Each scenario consisted of several tasks. The linguistic style users employed to communicate with the system (interaction style) was measured using the ratio of commands to the overall utterance length (keyword ratio) and the percentage of content words in the user's utterance that could be understood by the system (shared vocabulary). While the timing of help prompts did not affect the interaction style of younger users, it was early task-specific help supported older users in adapting their interaction style to the system's capabilities. Well-placed help prompts can significantly increase the usability of spoken dialogue systems for older people.
Michael White, Robert A. J. Clark, and Johanna D. Moore. Generating tailored, comparative descriptions with contextually appropriate intonation. Computational Linguistics, 36(2):159-201, 2010. [ bib | DOI ]
Generating responses that take user preferences into account requires adaptation at all levels of the generation process. This article describes a multi-level approach to presenting user-tailored information in spoken dialogues which brings together for the first time multi-attribute decision models, strategic content planning, surface realization that incorporates prosody prediction, and unit selection synthesis that takes the resulting prosodic structure into account. The system selects the most important options to mention and the attributes that are most relevant to choosing between them, based on the user model. Multiple options are selected when each offers a compelling trade-off. To convey these trade-offs, the system employs a novel presentation strategy which straightforwardly lends itself to the determination of information structure, as well as the contents of referring expressions. During surface realization, the prosodic structure is derived from the information structure using Combinatory Categorial Grammar in a way that allows phrase boundaries to be determined in a flexible, data-driven fashion. This approach to choosing pitch accents and edge tones is shown to yield prosodic structures with significantly higher acceptability than baseline prosody prediction models in an expert evaluation. These prosodic structures are then shown to enable perceptibly more natural synthesis using a unit selection voice that aims to produce the target tunes, in comparison to two baseline synthetic voices. An expert evaluation and f0 analysis confirm the superiority of the generator-driven intonation and its contribution to listeners' ratings.
Michael Pucher, Friedrich Neubarth, and Volker Strom. Optimizing phonetic encoding for Viennese unit selection speech synthesis. In A. Esposito et al., editor, COST 2102 Int. Training School 2009, LNCS, Heidelberg, 2010. Springer-Verlag. [ bib | .ps | .pdf ]
While developing lexical resources for a particular language variety (Viennese), we experimented with a set of 5 different phonetic encodings, termed phone sets, used for unit selection speech synthesis. We started with a very rich phone set based on phonological considerations and covering as much phonetic variability as possible, which was then reduced to smaller sets by applying transformation rules that map or merge phone symbols. The optimal trade-off was found measuring the phone error rates of automatically learnt grapheme-to-phone rules and by a perceptual evaluation of 27 representative synthesized sentences. Further, we describe a method to semi-automatically enlarge the lexical resources for the target language variety using a lexicon base for Standard Austrian German.
Songfang Huang and Steve Renals. Hierarchical Bayesian language models for conversational speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 18(8):1941-1954, January 2010. [ bib | DOI | http | .pdf ]
Traditional n-gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfitting of maximum-likelihood estimation and the lack of rich contextual knowledge sources. In this paper, we exploit a hierarchical Bayesian interpretation for language modeling, based on a nonparametric prior called the Pitman-Yor process. This offers a principled approach to language model smoothing, embedding the power-law distribution for natural language. Experiments on the recognition of conversational speech in multiparty meetings demonstrate that by using hierarchical Bayesian language models, we are able to achieve significant reductions in perplexity and word error rate.
Keywords: AMI corpus , conversational speech recognition , hierarchical Bayesian model , language model (LM) , meetings , smoothing
Michael Pucher, Friedrich Neubarth, Volker Strom, Sylvia Moosmüller, Gregor Hofer, Christian Kranzler, Gudrun Schuchmann, and Dietmar Schabus. Resources for speech synthesis of viennese varieties. In Proc. Int. Conf. on Language Resources and Evaluation, LREC'10, Malta, 2010. European Language Resources Association (ELRA). [ bib | .ps | .pdf ]
This paper describes our work on developing corpora of three varieties of Viennese for unit selection speech synthesis. The synthetic voices for Viennese varieties, implemented with the open domain unit selection speech synthesis engine Multisyn of Festival will also be released within Festival. The paper especially focuses on two questions: how we selected the appropriate speakers and how we obtained the text sources needed for the recording of these non-standard varieties. Regarding the first one, it turned out that working with a ‘prototypical’ professional speaker was much more preferable than striving for authenticity. In addition, we give a brief outline about the differences between the Austrian standard and its dialectal varieties and how we solved certain technical problems that are related to these differences. In particular, the specific set of phones applicable to each variety had to be determined by applying various constraints. Since such a set does not serve any descriptive purposes but rather is influencing the quality of speech synthesis, a careful design of such a (in most cases reduced) set was an important task.
Anna C. Janska and Robert A. J. Clark. Further exploration of the possibilities and pitfalls of multidimensional scaling as a tool for the evaluation of the quality of synthesized speech. In The 7th ISCA Tutorial and Research Workshop on Speech Synthesis, pages 142-147, 2010. [ bib | .pdf ]
Multidimensional scaling (MDS) has been suggested as a use- ful tool for the evaluation of the quality of synthesized speech. However, it has not yet been extensively tested for its applica- tion in this specific area of evaluation. In a series of experi- ments based on data from the Blizzard Challenge 2008 the relations between Weighted Euclidean Distance Scaling and Simple Euclidean Distance Scaling is investigated to understand how aggregating data affects the MDS configuration. These results are compared to those collected as mean opinion scores (MOS). The ranks correspond, and MOS can be predicted from an object's space in the MDS generated stimulus space. The big advantage of MDS over MOS is its diagnostic value; dimensions along which stimuli vary are not correlated, as is the case in modular evaluation using MOS. Finally, it will be attempted to generalize from the MDS representations of the thoroughly tested subset to the aggregated data of the larger-scale Blizzard Challenge.
Songfang Huang and Steve Renals. Power law discounting for n-gram language models. In Proc. IEEE ICASSP-10, pages 5178-5181, 2010. [ bib | DOI | http | .pdf ]
We present an approximation to the Bayesian hierarchical Pitman-Yor process language model which maintains the power law distribution over word tokens, while not requiring a computationally expensive approximate inference process. This approximation, which we term power law discounting, has a similar computational complexity to interpolated and modified Kneser-Ney smoothing. We performed experiments on meeting transcription using the NIST RT06s evaluation data and the AMI corpus, with a vocabulary of 50,000 words and a language model training set of up to 211 million words. Our results indicate that power law discounting results in statistically significant reductions in perplexity and word error rate compared to both interpolated and modified Kneser-Ney smoothing, while producing similar results to the hierarchical Pitman-Yor process language model.
Maria K. Wolters, Karl B. Isaac, and Steve Renals. Evaluating speech synthesis intelligibility using Amazon Mechanical Turk. In Proc. 7th Speech Synthesis Workshop (SSW7), pages 136-141, 2010. [ bib | .pdf ]
Microtask platforms such as Amazon Mechanical Turk (AMT) are increasingly used to create speech and language resources. AMT in particular allows researchers to quickly recruit a large number of fairly demographically diverse participants. In this study, we investigated whether AMT can be used for comparing the intelligibility of speech synthesis systems. We conducted two experiments in the lab and via AMT, one comparing US English diphone to US English speaker-adaptive HTS synthesis and one comparing UK English unit selection to UK English speaker-dependent HTS synthesis. While AMT word error rates were worse than lab error rates, AMT results were more sensitive to relative differences between systems. This is mainly due to the larger number of listeners. Boxplots and multilevel modelling allowed us to identify listeners who performed particularly badly, while thresholding was sufficient to eliminate rogue workers. We conclude that AMT is a viable platform for synthetic speech intelligibility comparisons.
P.L. De Leon, M. Pucher, and J. Yamagishi. Evaluation of the vulnerability of speaker verification to synthetic speech. In Proc. Odyssey (The speaker and language recognition workshop) 2010, Brno, Czech Republic, 2010. [ bib | .pdf ]
Steve Renals and Simon King. Automatic speech recognition. In William J. Hardcastle, John Laver, and Fiona E. Gibbon, editors, Handbook of Phonetic Sciences, chapter 22. Wiley Blackwell, 2010. [ bib ]
Ravi Chander Vipperla, Steve Renals, and Joe Frankel. Ageing voices: The effect of changes in voice parameters on ASR performance. EURASIP Journal on Audio, Speech, and Music Processing, 2010. [ bib | DOI | http | .pdf ]
With ageing, human voices undergo several changes which are typically characterized by increased hoarseness and changes in articulation patterns. In this study, we have examined the effect on Automatic Speech Recognition (ASR) and found that the Word Error Rates (WER) on older voices is about 9% absolute higher compared to those of adult voices. Subsequently, we compared several voice source parameters including fundamental frequency, jitter, shimmer, harmonicity and cepstral peak prominence of adult and older males. Several of these parameters show statistically significant difference for the two groups. However, artificially increasing jitter and shimmer measures do not effect the ASR accuracies significantly. Artificially lowering the fundamental frequency degrades the ASR performance marginally but this drop in performance can be overcome to some extent using Vocal Tract Length Normalisation (VTLN). Overall, we observe that the changes in the voice source parameters do not have a significant impact on ASR performance. Comparison of the likelihood scores of all the phonemes for the two age groups show that there is a systematic mismatch in the acoustic space of the two age groups. Comparison of the phoneme recognition rates show that mid vowels, nasals and phonemes that depend on the ability to create constrictions with tongue tip for articulation are more affected by ageing than other phonemes.
Keiichiro Oura, Keiichi Tokuda, Junichi Yamagishi, Mirjam Wester, and Simon King. Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis. In Proc. ICASSP, volume I, pages 4954-4957, 2010. [ bib | .pdf ]
In the EMIME project, we are developing a mobile device that performs personalized speech-to-speech translation such that a user's spoken input in one language is used to produce spoken output in another language, while continuing to sound like the user's voice. We integrate two techniques, unsupervised adaptation for HMM-based TTS using a word-based large-vocabulary continuous speech recognizer and cross-lingual speaker adaptation for HMM-based TTS, into a single architecture. Thus, an unsupervised cross-lingual speaker adaptation system can be developed. Listening tests show very promising results, demonstrating that adapted voices sound similar to the target speaker and that differences between supervised and unsupervised cross-lingual speaker adaptation are small.
Gregor Hofer, Korin Richmond, and Michael Berger. Lip synchronization by acoustic inversion. Poster at Siggraph 2010, 2010. [ bib | .pdf ]
Steve Renals and Thomas Hain. Speech recognition. In Alex Clark, Chris Fox, and Shalom Lappin, editors, Handbook of Computational Linguistics and Natural Language Processing. Wiley Blackwell, 2010. [ bib ]
Volker Strom and Simon King. A classifier-based target cost for unit selection speech synthesis trained on perceptual data. In Proc. Interspeech, Makuhari, Japan, 2010. [ bib | .ps | .pdf ]
Our goal is to automatically learn a PERCEPTUALLY-optimal target cost function for a unit selection speech synthesiser. The approach we take here is to train a classifier on human perceptual judgements of synthetic speech. The output of the classifier is used to make a simple three-way distinction rather than to estimate a continuously-valued cost. In order to collect the necessary perceptual data, we synthesised 145,137 short sentences with the usual target cost switched off, so that the search was driven by the join cost only. We then selected the 7200 sentences with the best joins and asked 60 listeners to judge them, providing their ratings for each syllable. From this, we derived a rating for each demiphone. Using as input the same context features employed in our conventional target cost function, we trained a classifier on these human perceptual ratings. We synthesised two sets of test sentences with both our standard target cost and the new target cost based on the classifier. A/B preference tests showed that the classifier-based target cost, which was learned completely automatically from modest amounts of perceptual data, is almost as good as our carefully- and expertly-tuned standard target cost.
Kallirroi Georgila, Maria Wolters, and Johanna D. Moore. Learning dialogue strategies from older and younger simulated users. In Proc. SIGDIAL, 2010. [ bib | .pdf ]
Older adults are a challenging user group because their behaviour can be highly variable. To the best of our knowledge, this is the first study where dialogue strategies are learned and evaluated with both simulated younger users and simulated older users. The simulated users were derived from a corpus of interactions with a strict system-initiative spoken dialogue system (SDS). Learning from simulated younger users leads to a policy which is close to one of the dialogue strategies of the underlying SDS, while the simulated older users allow us to learn more flexible dialogue strategies that accommodate mixed initiative. We conclude that simulated users are a useful technique for modelling the behaviour of new user groups.
Alice Turk, James Scobbie, Christian Geng, Cedric Macmartin, Ellen Bard, Barry Campbell, Catherine Dickie, Eddie Dubourg, Bill Hardcastle, Phil Hoole, Evia Kanaida, Robin Lickley, Satsuki Nakai, Marianne Pouplier, Simon King, Steve Renals, Korin Richmond, Sonja Schaeffler, Ronnie Wiegand, Kevin White, and Alan Wrench. The Edinburgh Speech Production Facility's articulatory corpus of spontaneous dialogue. The Journal of the Acoustical Society of America, 128(4):2429-2429, 2010. [ bib | DOI ]
The EPSRC‐funded Edinburgh Speech Production is built around two synchronized Carstens AG500 electromagnetic articulographs (EMAs) in order to capture articulatory∕acoustic data from spontaneous dialogue. An initial articulatory corpus was designed with two aims. The first was to elicit a range of speech styles∕registers from speakers, and therefore provide an alternative to fully scripted corpora. The second was to extend the corpus beyond monologue, by using tasks that promote natural discourse and interaction. A subsidiary driver was to use dialects from outwith North America: dialogues paired up a Scottish English and a Southern British English speaker. Tasks. Monologue: Story reading of “Comma Gets a Cure” [Honorof et al. (2000)], lexical sets [Wells (1982)], spontaneous story telling, diadochokinetic tasks. Dialogue: Map tasks [Anderson et al. (1991)], “Spot the Difference” picture tasks [Bradlow et al. (2007)], story‐recall. Shadowing of the spontaneous story telling by the second participant. Each dialogue session includes approximately 30 min of speech, and there are acoustics‐only baseline materials. We will introduce the corpus and highlight the role of articulatory production data in helping provide a fuller understanding of various spontaneous speech phenomena by presenting examples of naturally occurring covert speech errors, accent accommodation, turn taking negotiation, and shadowing.
Michael Pucher, Dietmar Schabus, Junichi Yamagishi, Friedrich Neubarth, and Volker Strom. Modeling and interpolation of Austrian German and Viennese dialect in HMM-based speech synthesis. Speech Communication, 52(2):164-179, 2010. [ bib | DOI ]
An HMM-based speech synthesis framework is applied to both Standard Austrian German and a Viennese dialectal variety and several training strategies for multi-dialect modeling such as dialect clustering and dialect-adaptive training are investigated. For bridging the gap between processing on the level of HMMs and on the linguistic level, we add phonological transformations to the HMM interpolation and apply them to dialect interpolation. The crucial steps are to employ several formalized phonological rules between Austrian German and Viennese dialect as constraints for the HMM interpolation. We verify the effectiveness of this strategy in a number of perceptual evaluations. Since the HMM space used is not articulatory but acoustic space, there are some variations in evaluation results between the phonological rules. However, in general we obtained good evaluation results which show that listeners can perceive both continuous and categorical changes of dialect varieties by using phonological transformations employed as switching rules in the HMM interpolation.
Maria K. Wolters, Florian Gödde, Sebastian Möller, and Klaus-Peter Engelbrecht. Finding patterns in user quality judgements. In Proc. ISCA Workshop Perceptual Quality of Speech Systems, Dresden, Germany, 2010. [ bib | .pdf ]
User quality judgements can show a bewildering amount of variation that is diffcult to capture using traditional quality prediction approaches. Using clustering, an ex- ploratory statistical analysis technique, we reanalysed the data set of a Wizard-of-Oz experiment where 25 users were asked to rate the dialogue after each turn. The sparse data problem was addressed by careful a priori parameter choices and comparison of the results of different cluster algorithms. We found two distinct classes of users, positive and critical. Positive users were generally happy with the dialogue system, and did not mind errors. Critical users downgraded their opinion of the system after errors, used a wider range of ratings, and were less likely to rate the system positively overall. These user groups could not be predicted by experience with spoken dialogue systems, attitude to spoken dialogue systems, anity with technology, demographics, or short-term memory capacity. We suggest that evaluation research should focus on critical users and discuss how these might be identified.
J. Yamagishi and S. King. Simple methods for improving speaker-similarity of HMM-based speech synthesis. In Proc. ICASSP 2010, Dallas, Texas, USA, 2010. [ bib | .pdf ]
Jonathan Kilgour, Jean Carletta, and Steve Renals. The Ambient Spotlight: Personal multimodal search without query. In Proc. ICMI-MLMI, 2010. [ bib | DOI | http | .pdf ]
The Ambient Spotlight is a prototype system based on personal meeting capture using a laptop and a portable microphone array. The system automatically recognises and structures the meeting content using automatic speech recognition, topic segmentation and extractive summarisation. The recognised speech in the meeting is used to construct queries to automatically link meeting segments to other relevant material, both multimodal and textual. The interface to the system is constructed around a standard calendar interface, and it is integrated with the laptop's standard indexing, search and retrieval.
Simon King. A tutorial on HMM speech synthesis (invited paper). In Sadhana - Academy Proceedings in Engineering Sciences, Indian Institute of Sciences, 2010. [ bib | .pdf ]
Statistical parametric speech synthesis, based on HMM-like models, has become competitive with established concatenative techniques over the last few years. This paper offers a non-mathematical introduction to this method of speech synthesis. It is intended to be complementary to the wide range of excellent technical publications already available. Rather than offer a comprehensive literature review, this paper instead gives a small number of carefully chosen references which are good starting points for further reading.
Atef Ben Youssef, Pierre Badin, and Gérard Bailly. Acoustic-to-articulatory inversion in speech based on statistical models. In Proc. AVSP 2010, pages 160-165, Hakone, Kanagawa, Japon, 2010. [ bib | .pdf ]
Two speech inversion methods are implemented and compared. In the first, multistream Hidden Markov Models (HMMs) of phonemes are jointly trained from synchronous streams of articulatory data acquired by EMA and speech spectral parameters; an acoustic recognition system uses the acoustic part of the HMMs to deliver a phoneme chain and the states durations; this information is then used by a trajectory formation procedure based on the articulatory part of the HMMs to resynthesise the articulatory movements. In the second, Gaussian Mixture Models (GMMs) are trained on these streams to directly associate articulatory frames with acoustic frames in context, using Maximum Likelihood Estimation. Over a corpus of 17 minutes uttered by a French speaker, the RMS error was 1.62 mm with the HMMs and 2.25 mm with the GMMs.
Pierre Badin, Atef Ben Youssef, Gérard Bailly, Frédéric Elisei, and Thomas Hueber. Visual articulatory feedback for phonetic correction in second language learning. In Workshop on Second Language Studies: Acquisition, Learning, Education and Technology, Tokyo, Japan, 2010. [ bib | .pdf ]
Orofacial clones can display speech articulation in an augmented mode, i.e. display all major speech articulators, including those usually hidden such as the tongue or the velum. Besides, a number of studies tend to show that the visual articulatory feedback provided by ElectroPalatoGraphy or ultrasound echography is useful for speech therapy. This paper describes the latest developments in acoustic-to-articulatory inversion, based on statistical models, to drive orofacial clones from speech sound. It suggests that this technology could provide a more elaborate feedback than previously available, and that it would be useful in the domain of Computer Aided Pronunciation Training