The Centre for Speech Technology Research, The university of Edinburgh

Publications by Mike Lincoln

mlincol1.bib

@inproceedings{zwyssig2012effect,
  author = {Zwyssig, E. and Renals, S. and Lincoln, M.},
  doi = {10.1109/ICASSP.2012.6288839},
  title = {{On the effect of SNR and superdirective beamforming in speaker diarisation in meetings}},
  abstract = {This paper examines the effect of sensor performance on speaker diarisation in meetings and investigates the use of more advanced beamforming techniques, beyond the typically employed delay-sum beamformer, for mitigating the effects of poorer sensor performance. We present super-directive beamforming and investigate how different time difference of arrival (TDOA) smoothing and beamforming techniques influence the performance of state-of-the-art diarisation systems. We produced and transcribed a new corpus of meetings recorded in the instrumented meeting room using a high SNR analogue and a newly developed low SNR digital MEMS microphone array (DMMA.2). This research demonstrates that TDOA smoothing has a significant effect on the diarisation error rate and that simple noise reduction and beamforming schemes suffice to overcome audio signal degradation due to the lower SNR of modern MEMS microphones.},
  year = {2012},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/zwyssig-dmma2-icassp12.pdf},
  booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on},
  pages = {4177--4180}
}

@inproceedings{zwyssig2012determining,
  author = {Zwyssig, E. and Renals, S. and Lincoln, M.},
  doi = {10.1109/ICASSP.2012.6288984},
  title = {Determining the number of speakers in a meeting using microphone array features},
  abstract = {The accuracy of speaker diarisation in meetings relies heavily on determining the correct number of speakers. In this paper we present a novel algorithm based on time difference of arrival (TDOA) features that aims to find the correct number of active speakers in a meeting and thus aid the speaker segmentation and clustering process. With our proposed method the microphone array TDOA values and known geometry of the array are used to calculate a speaker matrix from which we determine the correct number of active speakers with the aid of the Bayesian information criterion (BIC). In addition, we analyse several well-known voice activity detection (VAD) algorithms and verified their fitness for meeting recordings. Experiments were performed using the NIST RT06, RT07 and RT09 data sets, and resulted in reduced error rates compared with BIC-based approaches.},
  year = {2012},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2012/zwyssig-dia-icassp12.pdf},
  booktitle = {Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on},
  pages = {4765--4768}
}

@inproceedings{zwyssig2010,
  author = {Zwyssig, Erich and Lincoln, Mike and Renals, Steve},
  doi = {10.1109/ICASSP.2010.5495040},
  title = {A Digital Microphone Array for Distant Speech Recognition},
  booktitle = {Proc. IEEE ICASSP--10},
  abstract = {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.},
  year = {2010},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2010/zwyssig-icassp10.pdf},
  pages = {5106--5109}
}

@inproceedings{Ban00,
  author = {Bangham, J.A. and Cox, S.J. and Lincoln, M. and Marshall, I. and Tutt, M. and Wells, M},
  title = {Signing for the deaf using virtual humans},
  booktitle = {IEE Colloquium on Speech and Language processing for Disabled and Elderly},
  year = {2000},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2000/iee2000-04PaperAFinal.pdf},
  abstract = {Research at Televirtual (Norwich) and the University of East Anglia, funded predominantly by the Independent Television Commission and more recently by the UK Post Office also, has investigated the feasibility of using virtual signing as a communication medium for presenting information to the Deaf. We describe and demonstrate the underlying virtual signer technology, and discuss the language processing techniques and discourse models which have been investigated for information communication in a transaction application in Post Offices, and for presentation of more general textual material in texts such as subtitles accompanying television programmes.},
  categories = {visicast,sign language,translation,UEA}
}

@article{Wray04-LC04,
  author = {Wray, A. and Cox, S.J. and Lincoln, M. and Tryggvason, J.},
  title = {A Formulaic Approach to Translation at the Post Office: Reading the Signs},
  journal = {Language and Communication},
  number = {1},
  abstract = {TESSA is an interactive translation system designed to support transactions between a post office clerk and a deaf customer. The system translates the clerk's speech into British Sign Language (BSL), displayed on a screen, using a specially-developed avatar (virtual human). TESSA is a context-constrained exemplification of one of two basic approaches to machine translation, neither of which can currently fulfil all of the demands of successful automatic translation. Drawing on recent research in theoretical psycholinguistics, we show how TESSA is a convincing prototype model of one aspect of real human language processing. Ways are suggested of exploiting this parallel, potentially offering new possibilities for the future design of artificial language systems.},
  volume = {24},
  year = {2004},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2004/WrayCoxetal2004.pdf},
  pages = {59-75},
  categories = {visicast,sign language,translation,UEA}
}

@phdthesis{LIN99-phd,
  author = {Lincoln, M.},
  school = {University of East Anglia},
  title = {Characterization of Speakers for Improved Automatic Speech Recognition},
  abstract = {Automatic speech recognition technology is becoming increasingly widespread in many applications. For dictation tasks, where a single talker is to use the system for long periods of time, the high recognition accuracies obtained are in part due to the user performing a lengthy enrolment procedure to tune the parameters of the recogniser to their particular voice characteristics and speaking style. Interactive speech systems, where the speaker is using the system for only a short period of time (for example to obtain information) do not have the luxury of long enrolments and have to adapt rapidly to new speakers and speaking styles. This thesis discusses the variations between speakers and speaking styles which result in decreased recognition performance when there is a mismatch between the talker and the systems models. An unsupervised method to rapidly identify and normalise differences in vocal tract length is presented and shown to give improvements in recognition accuracy for little computational overhead. Two unsupervised methods of identifying speakers with similar speaking styles are also presented. The first, a data-driven technique, is shown to accurately classify British and American accented speech, and is also used to improve recognition accuracy by clustering groups of similar talkers. The second uses the phonotactic information available within pronunciation dictionaries to model British and American accented speech. This model is then used to rapidly and accurately classify speakers.},
  year = {1999},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1999/thesis.pdf},
  categories = {adaptation, ASR, speaker characteristics, BT, UEA}
}

@inproceedings{NistevalAMI06,
  author = {Hain, T. and Burget, L. and Burget, L. and dines, J. and Garau, G. and Karafiat, M. and Lincoln, M. and Vepa, J. and Wan, V.},
  title = {The {AMI} Meeting Transcription System: Progress and Performance},
  booktitle = {Proceedings of the Rich Transcription 2006 Spring Meeting Recognition Evaluation},
  year = {2006},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2006/AMIasr.nist06.pdf},
  abstract = {We present the AMI 2006 system for the transcription of speech in meetings. The system was jointly developed by multiple sites on the basis of the 2005 system for participation in the NIST RT'05 evaluations. The paper describes major developments such as improvements in automatic segmentation, cross-domain model adaptation, inclusion of MLP based features, improvements in decoding, language modelling and vocal tract length normalisation, the use of a new decoder, and a new system architecture. This is followed by a comprehensive description of the final system and its performance in the NIST RT'06s evaluations. In comparison to the previous year word error rate results on the individual headset microphone task were reduced by 20\% relative.},
  categories = {LVCSR, NIST Meeting Transcription Evaluation RT06S}
}

@inproceedings{Lin97,
  author = {Lincoln, M. and Cox, S.J. and Ringland, S.},
  title = {A fast method of speaker normalisation using formant estimation},
  booktitle = {5th European Conference on Speech Communication and Technology},
  year = {1997},
  abstract = {It has recently been shown that normalisation of vocal tract length can significantly increase recognition accuracy in speaker independent automatic speech recognition systems. An inherent difficulty with this technique is in automatically estimating the normalisation parameter from a new speaker's speech and previous techniques have typically relied on an exhaustive search to estimate this parameter. In this paper, we present a method of normalising utterances by a linear warping of the mel filter bank channels in which in which the normalisation parameter is estimated by fitting formant estimates to a probabilistic model. This method is fast, computitionally inexpensive and requires only a limited amount of data for estimation. It generates normalisations which are close to those which would be found by an exhaustive search. The normalisation is applied to a phoneme recognition task using the TIMIT database and results show a useful improvement over an un-normalised speaker independent system.},
  address = {Rhodes},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1997/lincoln-espeech-97.pdf},
  pages = {2095--2098},
  categories = {adaptation, vocal tract, speaker characteristics, BT, UEA}
}

@inproceedings{Cox02d,
  author = {Cox, S.J. and Lincoln, M. and Tryggvason, J and Nakisa, M and Wells, Mand Tutt, M. and Abbott, S},
  title = {{TESSA}, a system to aid communication with deaf people},
  booktitle = {ASSETS 2002, Fifth International {ACM SIGCAPH} Conference on Assistive Technologies},
  year = {2002},
  abstract = {{TESSA} is an experimental system that aims to aid transactions between a deaf person and a clerk in a Post Office by translating the clerks speech to sign language. A speech recogniser recognises speech from the clerk and the system then synthesizes the appropriate sequence of signs in British Sign language (BSL) using a speciallydeveloped avatar. By using a phrase lookup approach to language translation, which is appropriate for the highly constrained discourse in a Post Office, we were able to build a working system that we could evaluate. We summarise the results of this evaluation (undertaken by deaf users and Post office clerks), and discuss how the findings from the evaluation are being used in the development of an improved system},
  address = {Edinburgh, Scotland},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2002/Cox-Assets-2000.pdf},
  pages = {205-212},
  categories = {visicast,sign language,translation,UEA}
}

@inproceedings{NistevalAMI05,
  author = {Hain, T. and Burget, L. and Dines, J. and Garau, G. and Karafiat, M. and Lincoln, M. and McCowan, I. and Moore, D. and Wan, V. and Ordelman, R. and Renals, S.},
  title = {The 2005 {AMI} System for the transcription of Speech in Meetings},
  booktitle = {Proceedings of the Rich Transcription 2005 Spring Meeting Recognition Evaluation},
  year = {2005},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/AMIasr.nist2005.pdf},
  abstract = {In this paper we describe the 2005 AMI system for the transcription of speech in meetings used in the 2005 NIST RT evaluations. The system was designed for participation in the speech to text part of the evaluations, in particular for transcription of speech recorded with multiple distant microphones and independent headset microphones. System performance was tested on both conference room and lecture style meetings. Although input sources are processed using different frontends, the recognition process is based on a unified system architecture. The system operates in multiple passes and makes use of state of the art technologies such as discriminative training, vocal tract length normalisation, heteroscedastic linear discriminant analysis, speaker adaptation with maximum likelihood linear regression and minimum word error rate decoding. In this paper we describe the system performance on the official development and test sets for the NIST RT05s evaluations. The system was jointly developed in less than 10 months by a multi-site team and was shown to achieve competitive performance.},
  categories = {LVCSR, NIST Meeting Transcription Evaluation RT05S}
}

@inproceedings{Lin98,
  author = {Lincoln, M. and Cox, S.J. and Ringland, S.},
  title = {A Comparison of Two Unsupervised Approaches to Accent Identification},
  booktitle = {Int. Conf. on Spoken Language Processing},
  year = {1998},
  abstract = {The ability to automatically identify a speaker's accent would be very useful for a speech recognition system as it would enable the system to use both a pronunciation dictionary and speech models speci c to the accent, techniques which have been shown to improve accuracy. Here, we describe some experiments in unsupervised accent classi cation. Two techniques have been investigated to classify British- and Americanaccented speech: an acoustic approach, in which we analyse the pattern of usage of the distributions in the recogniser by a speaker to decide on his most probable accent, and a high-level approach in which we use a phonotactic model for classi cation of the accent. Results show that both techniques give excellent performance on this task which is maintained when testing is done on data from an independent dataset.},
  address = {Sydney},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/1998/lincoln-icslp-98.pdf},
  pages = {109-112},
  categories = {accent identification, speaker characteristics, BT, UEA}
}

@inproceedings{jyamagis:emime,
  author = {Yamagishi, Junichi and Lincoln, Mike and King, Simon and Dines, John and Gibson, Matthew and Tian, Jilei and Guan, Yong},
  title = {Analysis of Unsupervised and Noise-Robust Speaker-Adaptive {HMM}-Based Speech Synthesis Systems toward a Unified {ASR} and {TTS} Framework},
  booktitle = {Proc. Interspeech 2009},
  year = {2009},
  month = {September},
  address = {Edinburgh, U.K.},
  abstract = {For the 2009 Blizzard Challenge we have built an unsupervised version of the HTS-2008 speaker-adaptive HMM-based speech synthesis system for English, and a noise robust version of the systems for Mandarin. They are designed from a multidisciplinary application point of view in that we attempt to integrate the components of the TTS system with other technologies such as ASR. All the average voice models are trained exclusively from recognized, publicly available, ASR databases. Multi-pass LVCSR and confidence scores calculated from confusion network are used for the unsupervised systems, and noisy data recorded in cars or public spaces is used for the noise robust system. We believe the developed systems form solid benchmarks and provide good connections to ASR fields. This paper describes the development of the systems and reports the results and analysis of their evaluation.}
}

@article{Cox-ijhci03,
  author = {Cox, S.J. and Lincoln, M. and Nakisa, M. and Wells, M. and Tutt, M. and Abbott, S.},
  title = {The Development and Evaluation of a Speech to Sign Translation System to Assist Transactions},
  journal = {Int. Journal of Human Computer Interaction},
  number = {2},
  abstract = {The design, development, and evaluation of an experimental translation system that aims to aid transactions between a deaf person and a clerk in a post office (PO) is described. The system uses a speech recognizer to recognize speech from a PO clerk and then synthesizes recognized phrases in British Sign language (BSL) using a specially developed avatar. The main objective in developing this prototype system was to determine how useful it would be to a customer whose first language was BSL, and to discover what areas of the system required more research and development to make it more effective. The system was evaluated by 6 prelingually profoundly deaf people and 3 PO clerks. Deaf users and PO clerks were supportive of the system, but the former group required a higher quality of signing from the avatar and the latter a system that was less constrained in the phrases it could recognize; both these areas are being addressed in the next phase of development.},
  volume = {16},
  year = {2003},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2003/ijhci.pdf},
  pages = {141-161},
  categories = {visicast,sign language,translation,UEA}
}

@inproceedings{AMIMLMI05,
  author = {Hain, T. and Burget, L. and Dines, J. and Garau, G. and Karafiat, M. and Lincoln, M. and McCowan, I. and Moore, D. and Wan, V. and Ordelman, R. and Renals, S.},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2005/AMIsystemMLMI05.pdf},
  booktitle = {2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms},
  year = {2005},
  abstract = {The automatic processing of speech collected in conference style meetings has attracted considerable interest with several large scale projects devoted to this area. This paper describes the development of a baseline automatic speech transcription system for meetings in the context of the AMI (Augmented Multiparty Interaction) project. We present several techniques important to processing of this data and show the performance in terms of word error rates (WERs). An important aspect of transcription of this data is the necessary flexibility in terms of audio pre-processing. Real world systems have to deal with flexible input, for example by using microphone arrays or randomly placed microphones in a room. Automatic segmentation and microphone array processing techniques are described and the effect on WERs is discussed. The system and its components presented in this paper yield compettive performance and form a baseline for future research in this domain.},
  title = {The Development of the {AMI} System for the Transcription of Speech in Meetings}
}

@inproceedings{AMIsystemICASSP2007,
  author = {Hain, T. and Burget, L. and Dines, J. and Garau, G. and Karafiat, M. and Lincoln, M. and Vepa, J. and Wan, V.},
  title = {{The {AMI} System for the Transcription of Speech in Meetings}},
  booktitle = {Proc. {ICASSP}},
  year = {2007},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2007/ICASSP07.AMIasrsystem.pdf},
  abstract = {This paper describes the AMI transcription system for speech in meetings developed in collaboration by five research groups. The system includes generic techniques such as discriminative and speaker adaptive training, vocal tract length normalisation, heteroscedastic linear discriminant analysis, maximum likelihood linear regression, and phone posterior based features, as well as techniques specifically designed for meeting data. These include segmentation and cross-talk suppression, beam-forming, domain adaptation, web-data collection, and channel adaptive training. The system was improved by more than 20\% relative in word error rate compared to our previous system and was usd in the NIST RT’06 evaluations where it was found to yield competitive performance.},
  categories = {LVCSR, NIST Meeting Transcription Evaluation RT06S}
}

@inproceedings{Lin03,
  author = {Lincoln, M. and Cox, S.J.},
  title = {A Comparison of Language Processing Techniques for a Constrained Speech Translation System},
  booktitle = {IEEE Conference on Acoustics, Speech and Signal Processing},
  year = {2003},
  address = {Hong Kong},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2003/icassp2003.pdf},
  abstract = {A system designed to allow Post Office counter clerks to communicate with deaf customers by translating speech into sign language is described. The system uses approximately 370 pre-stored phrases which may be signed to the customer using a specially designed avatar. The clerk is unable to memorise this number of phrases and therefore the system attempts to map from their input speech to the semantically equivalent pre-stored phrase. We describe a number of language processing techniques developed to perform the mapping, and give results obtained using alternative formulations of the phrases from a number of speakers. We then give results for recognised speech input and show how mis-recognitions effect the mapping system. Best performance is obtained using a mapping system based on an entropy weighted, vector based distance measure between the test phrase and each of the signed phrases.},
  categories = {visicast,sign language,translation,UEA}
}

@inproceedings{zwyssig2013-overlap_SS_MEMS,
  author = {Zwyssig, E. and Faubel, F. and Renals, S. and Lincoln, M.},
  doi = {10.1109/ICASSP.2013.6639033},
  title = {Recognition of overlapping speech using digital {MEMS} microphone arrays},
  booktitle = {Proc IEEE ICASSP},
  year = {2013},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2013/zwyssig3344-final.pdf},
  abstract = {This paper presents a new corpus comprising single and overlapping speech recorded using digital MEMS and analogue microphone arrays. In addition to this, the paper presents results from speech separation and recognition experiments on this data. The corpus is a reproduction of the multi-channel Wall Street Journal audio-visual corpus (MC-WSJ-AV), containing recorded speech in both a meeting room and an anechoic chamber using two different microphone types as well as two different array geometries. The speech separation and speech recognition experiments were performed using SRP-PHAT-based speaker localisation, superdirective beamforming and multiple post-processing schemes, such as residual echo suppression and binary masking. Our simple, cMLLR-based recognition system matches the performance of state-of-the-art ASR systems on the single speaker task and outperforms them on overlapping speech. The corpus will be made publicly available via the LDC in spring 2013.}
}

@inproceedings{joachim_fainberg_improving_2016,
  author = {Fainberg, Joachim and Bell, Peter and Lincoln, Mike and Renals, Steve},
  title = {Improving Children's Speech Recognition through Out-of-Domain Data Augmentation},
  abstract = {Children’s speech poses challenges to speech recognition due to strong age-dependent anatomical variations and a lack of large, publicly-available corpora. In this paper we explore data augmentation for children’s speech recognition using stochastic feature mapping (SFM) to transform out-of-domain adult data for both GMM-based and DNN-based acoustic models. We performed experiments on the English PF-STAR corpus, augmenting using WSJCAM0 and ABI. Our experimental results indicate that a DNN acoustic model for childrens speech can make use of adult data, and that out-of-domain SFM is more accurate than in-domain SFM.},
  address = {San Francisco, USA},
  month = {September},
  year = {2016},
  pdf = {http://www.cstr.inf.ed.ac.uk/downloads/publications/2016/master.pdf},
  booktitle = {Proc. Interspeech},
  categories = {speech recognition, data augmentation, children’s speech}
}