skip to content

Cambridge Language Sciences

Interdisciplinary Research Centre
 

Research

My research field is the statistical modeling of speech and language. I develop models and algorithms that make it possible for computers to take text or speech and extract its content using computationally efficient mathematical models. This makes it possible to transcribe speech into text, to translate from one language into another, and to generate synthetic speech from text.

Publications

Key publications: 

Iglesias, G.,  Allauzen, C., Byrne, W., de Gispert, A., Riley, M. (2011).  Hierarchical phrase-based translation representations. Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing.  Edinburgh, UK.

de Gispert, A., Iglesias, G., Blackwood, G., Banga, E.R., Byrne, W. (2010) Hierarchical phrase-based translation with weighted finite state transducers and shallow-N grammars.  Computational Linguistics, September 2010.

Shannon, M., Byrne, W. (2009). Autoregressive HMMs for speech synthesis.  Proceedings of the 10th International Conference of the International Speech Communication Association: INTERSPEECH  2009

Deng, Y.,  Byrne, W. (2008). HMM word and phrase alignment for statistical machine translation. IEEE Transactions on Audio, Speech, and Language Processing.

Kumar, S, Byrne W. (2004). Minimum Bayes-risk decoding for statistical machine translation, Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL 2004.

Publications (from Symplectic)

Conference proceedings

2022 (Accepted for publication)

  • Saunders, D., sallis, R. and Byrne, W., 2022 (Accepted for publication). First the worst: Finding better gender translations during beam search
    Doi: http://doi.org/10.17863/CAM.82514
  • 2020

  • Saunders, D. and Byrne, B., 2020. Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem
  • Saunders, D., Stahlberg, F. and Byrne, B., 2020. Using Context in Neural Machine Translation Training Objectives
  • 2019

  • Stahlberg, F., Bryant, C. and Byrne, B., 2019. Neural Grammatical Error Correction with Finite State Transducers
  • Stahlberg, F. and Byrne, B., 2019. The CUED's Grammatical Error Correction Systems for BEA-2019
  • Stahlberg, F., Saunders, D., Gispert, AD. and Byrne, B., 2019. Cued@wmt19:ewc&lms
  • Stahlberg, F. and Byrne, B., 2019. On NMT Search Errors and Model Errors: Cat Got Your Tongue?
  • 2018 (No publication date)

  • Stahlberg, F., Hasler, E., Waite, A. and Byrne, WJ., 2018 (No publication date). Syntactically Guided Neural Machine Translation
  • Dall, R., Tomalin, M., Wester, M., Byrne, WJ. and King, S., 2018 (No publication date). Investigating Automatic and Human Filled Pause Insertion for Synthetic Speech
  • Byrne, WJ. and Horvat, M., 2018 (No publication date). A Graph-Based Approach to String Regeneration
  • Byrne, WJ. and Shannon, M., 2018 (No publication date). FAST, LOW-ARTIFACT SPEECH SYNTHESIS CONSIDERING GLOBAL VARIANCE
  • 2018 (Accepted for publication)

  • Saunders, D., Stahlberg, F., De Gispert, A. and Byrne, WJ., 2018 (Accepted for publication). Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), v. P18-2051
  • Iglesias, G., Tambellini, W., de Gispert, A., Hasler, E. and Byrne, WJ., 2018 (Accepted for publication). Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
    Doi: http://doi.org/10.17863/CAM.35282
  • Hasler, E., de Gspert, A., Iglesias, G. and Byrne, WJ., 2018 (Accepted for publication). Neural Machine Translation Decoding with Terminology Constraints
  • 2018

  • Stahlberg, F., Gispert, AD. and Byrne, B., 2018. The University of Cambridge's Machine Translation Systems for WMT18
  • Stahlberg, F., Saunders, D. and Byrne, B., 2018. An Operation Sequence Model for Explainable Neural Machine Translation
  • Stahlberg, F., Saunders, D., Iglesias, G. and Byrne, WJ., 2018. Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation AMTA 2018, v. 1
  • 2017 (Accepted for publication)

  • Hasler, E., Stahlberg, F., tomalin, M., de Gispert, A. and Byrne, WJ., 2017 (Accepted for publication). A Comparison of Neural Models for Word Ordering Proceedings of the 10th International Conference on Natural Language Generation,
    Doi: http://doi.org/10.18653/v1/W17-3531
  • 2017

  • Stahlberg, F., Hasler, E., Saunders, D. and Byrne, W., 2017. SGNMT -- A Flexible NMT Decoding Platform for Quick Prototyping of New Models and Search Strategies
  • Stahlberg, F., de Gispert, A., Hasler, E. and Byrne, W., 2017. Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, v. 2, Short Papers
  • Sterckx, L., Naradowsky, J., Byrne, WJ., Demeester, T. and Develder, C., 2017. Break it Down for Me: A Study in Automated Lyric Annotation
    Doi: http://doi.org/10.17863/CAM.11857
  • Stahlberg, F. and Byrne, W., 2017. Unfolding and Shrinking Neural Machine Translation Ensembles
  • 2016

  • Stahlberg, F., Hasler, E. and Byrne, B., 2016. The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
  • Beck, D., De Gispert, A., Iglesias, G., Waite, A. and Byrne, B., 2016. Speed-constrained tuning for statistical machine translation using Bayesian optimization 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016 - Proceedings of the Conference,
    Doi: http://doi.org/10.18653/v1/n16-1100
  • 2015 (Accepted for publication)

  • Byrne, WJ. and Waite, A., 2015 (Accepted for publication). The Geometry of Statistical Machine Translation
  • 2015

  • Iglesias, G., De Gispert, A. and Byrne, B., 2015. Transducer disambiguation with sparse topological features Conference Proceedings - EMNLP 2015: Conference on Empirical Methods in Natural Language Processing,
    Doi: http://doi.org/10.18653/v1/d15-1273
  • De Gispert, A., Iglesias, G. and Byrne, B., 2015. Fast and accurate preordering for SMT using neural networks NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference,
    Doi: http://doi.org/10.3115/v1/n15-1105
  • Horvat, M., Copestake, A. and Byrne, W., 2015. Hierarchical statistical semantic realization for minimal recursion semantics IWCS 2015 - Proceedings of the 11th International Conference on Computational Semantics,
  • 2014

  • De Gispert, A., Tomalin, M. and Byrne, W., 2014. Word ordering with phrase-based grammars 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014,
    Doi: http://doi.org/10.3115/v1/e14-1028
  • Jehl, L., De Gispert, A., Hopkins, M. and Byrne, W., 2014. Source-side preordering for translation using logistic regression and depth-first branch-And-bound search 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014,
    Doi: http://doi.org/10.3115/v1/e14-1026
  • Xiao, T., De Gispert, A., Zhu, J. and Byrne, B., 2014. Effective incorporation of source syntax into hierarchical phrase-based translation COLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers,
  • 2011

  • Shannon, SM. and Byrne, WJ., 2011. Autoregressive clustering for HMM speech synthesis Proceedings of the 11th Annual Conference of the International Speech Communication,
  • Iglesias, G., Allauzen, C., Byrne, W., de Gispert, A. and Riley, M., 2011. Hierarchical Phrase-based Translation Representations Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing,
  • Shannon, M., Zen, H. and Byrne, W., 2011. The Effect of Using Normalized Models in Statistical Speech Synthesis Proceedings of the 12$^th$ Annual Conference of the International Speech Communication Association,
  • 2010

  • Blackwood, GW., de Gispert, A. and Byrne, WJ., 2010. Efficient path counting transducers for minimum Bayes-risk decoding of statistical machine translation lattices Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics,
  • Blackwood, GW., de Gispert, A. and Byrne, WJ., 2010. Fluency constraints for minimum Bayes-risk decoding of statistical machine translation lattices Proceedings of the 23rd International Conference on Computational Linguistics,
  • Gibson, M., Hirsimaki, T., Karhila, R., Kurimo, M. and Byrne, WJ., 2010. Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing,
    Doi: http://doi.org/10.1109/ICASSP.2010.5495196
  • De Gispert, A., Juan, P. and Byrne, W., 2010. Hierarchical phrase-based translation grammars extracted from alignment posterior probabilities EMNLP 2010 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference,
  • Pino, J., Iglesias, G., de Gispert, A., Blackwood, GW. and Byrne, WJ., 2010. The CUED HiFST system for the WMT10 translation shared task
  • Kurimo, M., Byrne, W., Dines, J., Garner, PN., Gibson, M., Guan, Y., Hirsimäki, T., Karhila, R., King, S., Liang, H., Oura, K., Saheer, L., Shannon, M., Shiota, S., Tian, J., Tokuda, K., Wester, M., Wu, YJ. and Yamagishi, J., 2010. Personalising speech-to-speech translation in the EMIME project ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference,
  • 2009

  • Brunning, JJJ., de Gispert, A. and Byrne, WJ., 2009. Context-dependent alignment models for statistical machine translation Human Language Technologies: the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics,
  • Iglesias, G., de Gispert, A. and Byrne, WJ., 2009. Hierarchical phrase-based translation with weighted finite state transducers Proceedings of Human Language Technologies: the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics,
  • de Gispert, A., Virpioja, S., Kurimo, M. and Byrne, WJ., 2009. Minimum Bayes risk combination of translation hypotheses from alternative morphological decompositions Human Language Technologies: the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics,
  • Iglesias, G., de Gispert, A., Banga, ER. and Byrne, WJ., 2009. Rule filtering by pattern for efficient hierarchical translation Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics,
  • Shannon, SM. and Byrne, WJ., 2009. Autoregressive HMMs for speech synthesis
  • 2008

  • Blackwood, GW., de Gispert, A., Brunning, JJJ. and Byrne, WJ., 2008. Large-scale statistical machine translation with weighted finite state transducers
  • Blackwood, GW., de Gispert, A., Brunning, JJJ. and Byrne, WJ., 2008. European language translation with weighted finite state transducers: the CUED MT system Proceedings of the ACL 2008 Third Workshop on Statistical Machine Translation,
  • Blackwood, GW., de Gispert, A. and Byrne, WJ., 2008. Phrasal segmentation models for statistical machine translation Proceedings of the 22nd International Conference on Computational Linguistics, v. 1
  • 2007

  • Liu, XA., Byrne, WJ., Gales, MJF., De Gispert, A., Tomalin, M., Woodland, PC. and Yu, K., 2007. Discriminative language model adaptation for Mandarin broadcast speech transcription and translation 2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings,
    Doi: http://doi.org/10.1109/asru.2007.4430101
  • Liu, XA., Byrne, WJ., Gales, MJF., de Gispert, A., Tomalin, M., Woodland, PC. and Yu, K., 2007. Discriminative language model adaptation for Mandarin broadcast speech transcription and translation IEEE Workshop on Automatic Speech Recognition & Understanding, 2007,
    Doi: http://doi.org/10.1109/ASRU.2007.4430101
  • Sim, KC., Byrne, WJ., Gales, MJF., Sahbi, H. and Woodland, PC., 2007. Consensus network decoding for statistical machine translation system combination IEEE International Conference on Acoustics Speech and Signal Processing, v. 4
    Doi: http://doi.org/10.1109/ICASSP.2007.367174
  • 2006

  • Byrne, W., 2006. Minimum Bayes risk estimation and decoding in large vocabulary continuous speech recognition Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06); Vol. 1,
  • Mathias, L. and Byrne, W., 2006. Statistical phrase-based speech translation IEEE International Conference on Acoustics Speech and Signal Processing, v. 1
    Doi: http://doi.org/10.1109/ICASSP.2006.1660082
  • 2005

  • Tsakalidis, S. and Byrne, WJ., 2005. Acoustic training from heterogeneous data sources: experiments in Mandarin conversational telephone speech transcription IEEE International Conference on Acoustics Speech and Signal Processing, v. 1
    Doi: http://doi.org/10.1109/ICASSP.2005.1415150
  • Venkataramani, V. and Byrne, WJ., 2005. Lattice segmentation and support vector machines for large vocabulary continuous speech recognition IEEE International Conference on Acoustics Speech and Signal Processing, v. 1
    Doi: http://doi.org/10.1109/ICASSP.2005.1415239
  • Deng, Y. and Byrne, WJ., 2005. HMM word and phrase alignment for statistical machine translation Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP'05),
  • Kumar, S. and Byrne, WJ., 2005. Local phrase reordering models for statistical machine translation Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP'05),
  • Psutka, J., Ircing, P., Psutka, JV., Hajic, J., Byrne, WJ. and Mirovsky, J., 2005. Automatic transcription of Czech, Russian, and Slovak spontaneous speech in the MALACH project Proceedings of the 9th European Conference on Speech Communciation and Technology (EUROSPEECH/INTERSPEECH),
  • 2004

  • Doumpiotis, V. and Byrne, WJ., 2004. Pinched lattice minimum Bayes risk discriminative training for large vocabulary continuous speech recognition INTERSPEECH 2004: Proceedings of the 8th International Conference on Spoken Language Processing (ICSLP),
  • Kumar, S. and Byrne, WJ., 2004. Minimum Bayes-risk decoding for statistical machine translation Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL'04),
  • Shafran, I. and Byrne, WJ., 2004. Task-specific minimum Bayes-risk decoding using learned edit distance INTERSPEECH 2004: Proceedings of the 8th International Conference on Spoken Language Processing (ICSLP),
  • Psutka, J., Hajic, J. and Byrne, WJ., 2004. The development of ASR for Slavic languages in the MALACH project IEEE International Conference on Acoustics Speech and Signal Processing, v. 3
  • Psutka, J., Ircing, P., Hajic, J., Radova, V., Psutka, JV., Byrne, WJ. and Gustman, S., 2004. Issues in annotation of the Czech spontaneous speech corpus in the MALACH project Proceedings of the 4th International Conference on Language Resources and Evaluation, v. 2
  • Byrne, W., 2004. Minimum Bayes risk estimation and decoding in large vocabulary continuous speech recognition Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06); Vol. 1,
  • 2003

  • Gustman, S., Soergel, D., Oard, D., Byrne, W., Picheny, M., Ramabhadran, B. and Greenberg, D., 2003. Supposting access to large digital oral history archives Proceedings of the Second Acm/Ieee-Cs Joint Conference on Digital Libraries: Jcdl 2002,
  • Venkataramani, V., Chakrabartty, SA. and Byrne, WJ., 2003. Support vector machines for segmental minimum Bayes risk decoding of continuous speech Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding,
  • Doumpiotis, V., Tsakalidis, S. and Byrne, WJ., 2003. Lattice segmentation and minimum Bayes risk discriminative training Proceedings of the 8th European Conference on Speech Communication and Technology; EUROSPEECH'03; Vol. 3,
  • Psutka, J., Iljuchin, I., Ircing, P., Psutka, JV., Trejbal, V., Byrne, WJ., Hajic, J. and Gustman, S., 2003. Building LVCSR system for transcription of spontaneously pronounced Russian testimonies in the MALACH project: initial steps and first results Proceedings of the 6th International Conference on Text, Speech and Dialogue (TSD'03), v. 2807
  • Psutka, J., Ircing, P., Psutka, JV., Radova, V., Byrne, WJ., Hajic, J. and Gustman, S., 2003. Towards automatic transcription of spontaneous Czech speech in the MALACH project Proceedings of the 6th International Conference on Text, Speech and Dialogue (TSD'03), v. 2807
  • Psutka, J., Ircing, P., Psutka, JV., Radova, V., Byrne, WJ., Hajic, J., Mirovsky, J. and Gustman, S., 2003. Large vocabulary ASR for spontaneous Czech in the MALACH project Proceedings of the 8th European Conference on Speech Communication and Technology; EUROSPEECH'03; Vol. 3, v. 8
  • Byrne, W., Khudanpur, W., Kim, S., Kumar, S., Pecina, P., Virga, P., Xu, P. and Yarowsky, D., 2003. The John-Hopkins University 2003 Chinese-English machine translation system
  • Doumpiotis, V., Tsakalidis, S. and Byrne, WJ., 2003. Discriminative training for segmental minimum Bayes-risk decoding Proceedings of the 28th IEEE International Conference on International Conference on Acoustics, Speech, and Signal Processing (ICASSP); Vol. 1: Speech Processing, v. 1
  • Ikeno, A., Pellom, B., Cer, D., Thornton, A., Brenier, JM., Jurafsky, D., Ward, W. and Byrne, W., 2003. Issues in recognition of spanish-accented spontaneous english Proceedings of the ISCA & IEEE Workshop on Spontaneous Speech Processing and Recognition (SSPR-2003),
  • Kolak, O., Byrne, WJ. and Resnik, P., 2003. A generative probabilistic OCR model for NLP applications Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL'03),
  • Kumar, S. and Byrne, WJ., 2003. A weighted finite state transducer implementation of the alignment template model for statistical machine translation Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL'03),
  • Oard, D., Doermann, D., Dorr, B., He, D., Resnik, P., Weinberg, A., Byrne, WJ., Khudanpur, S., Yarowsky, D., Leuski, A., Koehn, P. and Knight, K., 2003. Desparately seeking Cebuano Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL'03),
  • 2002

  • Kumar, S. and Byrne, WJ., 2002. Risk based lattice cutting for segmental minimum Bayes-risk decoding Proceedings of the 7th International Conference on Spoken Language (INTERSPEECH 2002),
  • Tsakalidis, S., Doumpiotis, V. and Byrne, WJ., 2002. Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation Proceedings of the 7th International Conference on Spoken Language (INTERSPEECH 2002),
  • Zheng, F., Song, Z., Fung, P. and Byrne, WJ., 2002. Reducing pronunciation lexicon confusion and using more data without phonetic transcription for pronunciation modeling Proceedings of the 7th International Conference on Spoken Language (INTERSPEECH 2002),
  • Oard, DW., Demner Fushman, D., Hajic, J., Ramabhadran, B., Gustman, S., Byrne, WJ., Soergel, D., Dorr, B., Resnik, P. and Picheny, M., 2002. Automatic transcription of Czech language oral history in the MALACH project: resources and initial experiments Proceedings of the 5th International Conference on Text, Speech and Dialogue Conference, v. 2448
  • Psutka, J., Ircing, P., Psutka, JV., Radova, V., Byrne, WJ., Hajic, J., Gustman, S. and Ramabhadran, B., 2002. Automatic transcription of Czech language oral history in the MALACH project: resources and initial experiments Proceedings of the 5th International Conference on Text, Speech and Dialogue Conference, v. 2448
  • Ward, W., Krech, H., Yu, X., Herold, K., Figgs, G., Ikeno, A., Jurafsky, D. and Byrne, WJ., 2002. Lexicon adaptation for LVCSR: speaker idiosyncracies, non-native speakers, and pronunciation choice
  • Kumar, S. and Byrne, WJ., 2002. Minimum Bayes-risk word alignments of bilingual texts Proceedings of the 7th International Conference on Empirical Methods in Natural Language Processing,
  • 2001

  • Byrne, WJ. and Venkataramani, V., 2001. MLLR adaptation techniques for pronunciation modeling Proceedings of the IEEE International Workshop on Automatic Speech Recognition and Understanding,
  • Goel, V., Kumar, S. and Byrne, WJ., 2001. Confidence based lattice segmentation and minimum Bayes-risk decoding Proceedings of the 7th European Conference on Speech Communication and Technology, v. 4
  • Gunawardana, A. and Byrne, WJ., 2001. Discriminative speaker adaptation with conditional maximum likelihood linear regression Proceedings of the 7th European Conference on Speech Communication and Technology, v. 2
  • Ircing, P., Krbec, P., Hajic, J., Psutka, J., Khudanpur, S., Jelinek, F. and Byrne, WJ., 2001. On large vocabulary continuous speech recognition of highly inflectional language - Czech Proceedings of the 7th European Conference on Speech Communication and Technology, v. 1
  • Zheng, F., Song, Z., Fung, P. and Byrne, WJ., 2001. Modeling pronunciation variation using context-dependent weighting and B/S refined acoustic modeling Proceedings of the 7th European Conference on Speech Communication and Technology; Vol. 1,
  • Gunawardana, A. and Byrne, WJ., 2001. Convergence of DLLR rapid speaker adaptation algorithms Proceedings of the ISCA ITRW on Adaptation Methods for Speech Recognition,
  • 2000

  • Gunawardana, A. and Byrne, WJ., 2000. Robust estimation for rapid adaptation using discounted likelihood techniques Proceedings of the IEEE International Conference on International Conference on Acoustics, Speech, and Signal Processing (ICASSP); Vol 2; Signal Processing Theory and Methods II,
  • McDonough, J., Kumar, S. and Byrne, WJ., 2000. On the incremental addition of regression classes for speaker adaptation Proceedings of the IEEE International Conference on International Conference on Acoustics, Speech, and Signal Processing (ICASSP); Vol 3; Speech processing II,
  • Byrne, W., Beyerlein, P., Huerta, S., Khudanpur, S., Marthi, B., Morgan, J., Peterek, J., Picone, J., Vergyri, D. and Wang, W., 2000. Towards language independent acoustic modelling Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding,
  • Byrne, WJ., Beyerlein, P., Huerta, J., Khudanpur, S., Marthi, B., Morgan, J., Peterek, N., Picone, J., Vergyri, D. and Wang, W., 2000. Towards language independent acoustic modeling IEEE International Conference on Acoustics Speech and Signal Processing, v. 2
  • Goel, V., Kumar, S. and Byrne, WJ., 2000. Segmental minimum Bayes-risk ASR voting strategies Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP 2000), v. 3
  • Li, A., Zheng, F., Byrne, WJ., Fung, P., Kamm, T., Liu, Y., Song, Z., Ruhi, U., Venkataramani, V. and Chen, XX., 2000. CASS: A phonetically transcribed corpus of Mandarin spontaneous speech Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP 2000), v. 1
  • Vergyri, D., Tsakalidis, S. and Byrne, WJ., 2000. Minimum risk acoustic clustering for multilingual acoustic model combination Proceedings of the 6th International Conference on Spoken Language Processing (ICSLP 2000), v. 3
  • 1999

  • Byrne, WJ. and Gunawardana, A., 1999. Discounted likelihood linear regression for rapid adaptation Proceedings of the 6th European Conference on Speech Communication and Technology (EUROSPEECH'99),
  • Goel, V. and Byrne, WJ., 1999. Task dependent loss functions in speech recognition: A-star search over recognition lattices Proceedings of the 6th European Conference on Speech Communication and Technology (EUROSPEECH'99),
  • McDonough, J. and Byrne, WJ., 1999. Single-pass adapted training with all-pass transforms Proceedings of the 6th European Conference on Speech Communication and Technology (EUROSPEECH'99),
  • McDonough, JW. and Byrne, WJ., 1999. Speaker adaptation with all-pass transforms Proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), v. 2
  • Byrne, W., Finke, M., Khunanpur, S., McDonough, J., Nock, H., Riley, M., Saraclar, M., Wooters, C. and Zavaliagkos, G., 1999. Pronunciation modelling using a hand-labelled corpus for conversational speech recognition Proceedings of the 1998 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '98, v. 1
    Doi: http://doi.org/10.1109/ICASSP.1998.674430
  • Byrne, W. and Gunawardana, A., 1999. Convergence of EM variants Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding,
  • Byrne, WJ., Hajič, J., Ircing, P., Jelinek, S., Khudanpur, S., McDonough, J., Peterek, N. and Psutka, J., 1999. Large vocabulary speech recognition for read and broadcast Czech Text, Speech and Dialogue: 2nd International Workshop TSD’99,,
    Doi: http://doi.org/10.1007/3-540-48239-3_43
  • Goel, V. and Byrne, WJ., 1999. Task dependent loss functions in speech recognition: application to named entity extraction Proceedings of the ESCA ETRW Workshop on Accessing Information in Spoken Audio,
  • 1998

  • McDonough, J., Byrne, WJ. and Luo, X., 1998. Speaker normalization with all-pass transforms Proceedings of the 5th International Conference on Spoken Language Processing (ICSLP'98),
  • Byrne, W., Khudanpur, S., Knodt, E. and Bernstein, J., 1998. Is automatic speech recognition ready for non-native speech? A data collection effort and initial experiments in modelling conversational Hispanic English Royal Institute of Technology Speech Music and Hearing, v. 1998
  • Goel, V., Byrne, WJ. and Khudanpur, S., 1998. LVCSR rescoring with modified loss functions: a decision theoretic perspective Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP); Vol 1; Speech Processing I,
  • Byrne, W., Finke, M., Khunanpur, S., Ljolje, A., McDonough, J., Nock, H., Riley, M., Saraclar, M., Wooters, C. and Zavaliagkos, G., 1998. Pronunciation modelling using a hand-labelled corpus for conversational speech recognition Proceedings of the 1998 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '98, v. 1
  • 1997

  • Byrne, WJ., Finke, M., Khudanpur, S., McDonough, J., Nock, H., Riley, M., Saraclar, M., Wooters, C. and Zavaliagkos, G., 1997. Pronunciation modelling for conversational speech recognition: a status report from WS97 Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding,
    Doi: http://doi.org/10.1109/ASRU.1997.658973
  • 1996

  • Byrne, WJ., 1996. Information geometry and maximum likelihood criteria Proceedings of the 30th Annual Conference on Information Sciences and Systems, v. 30
  • 1985

  • Byrne, WJ., Robinson, J. and Shamma, S., 1985. The auditory processing and recognition of speech Proceedings of the Speech and Natural Language Workshop,
  • Byrne, WJ., Zapp, R., Flynn, P. and Siegel, M., 1985. Adaptive filtering in microwave remote heart monitors The Inference Group Website, Cavendish Laboratory, Cambridge University,
  • Datasets

    2018 (No publication date)

  • Hasler, E., de, GA., Stahlberg, F., Waite, A. and Byrne, B., 2018 (No publication date). Research data supporting “Source Sentence Simplification for Statistical Machine Translation”
  • Journal articles

    2016 (Accepted for publication)

  • Hasler, EC., de Gispert, A., Stahlberg, F., Waite, A. and Byrne, WJ., 2016 (Accepted for publication). Source sentence simplification for statistical machine translation Computer Speech & Language, v. 45
    Doi: http://doi.org/10.1016/j.csl.2016.12.001
  • 2014

  • Allauzen, C., Byrne, B., de Gispert, A., Iglesias, G. and Riley, M., 2014. Pushdown automata in statistical machine translation Computational Linguistics, v. 40
    Doi: http://doi.org/10.1162/COLI_a_00197
  • 2013

  • Shannon, M., Zen, H. and Byrne, W., 2013. Autoregressive Models for Statistical Parametric Speech Synthesis Audio, Speech, and Language Processing, IEEE Transactions on, v. 21
    Doi: http://doi.org/10.1109/TASL.2012.2227740
  • De Gispert, A., Blackwood, G., Iglesias, G. and Byrne, W., 2013. N-gram posterior probability confidence measures for statistical machine translation: An empirical study Machine Translation, v. 27
    Doi: http://doi.org/10.1007/s10590-012-9132-2
  • 2012

  • Pino, J., Waite, A. and Byrne, W., 2012. Simple and Efficient Model Filtering in Statistical Machine Translation The Prague Bulletin of Mathematical Linguistics, v. 98
    Doi: 10.2478/v10108-012-0005-x
  • 2011

  • Gibson, M. and Byrne, W., 2011. Unsupervised intra-lingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction IEEE Transactions on Audio, Speech, and Language Processing, v. 19
  • Dines, J., Liang, H., Saheer, L., Gibson, M., Byrne, W., Oura, K., Tokuda, K., Yamagishi, J., King, S., Wester, M., Hirsimaki, T., Karhila, R. and Kurimo, M., 2011. Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis Computer Speech and Language,
    Doi: http://doi.org/10.1016/j.csl.2011.08.003
  • Dines, J., Liang, H., Saheer, L., Gibson, M., Byrne, W., Oura, K., Tokuda, K., Yamagishi, J., King, S., Wester, M., Hirsimäki, T., Karhila, R. and Kurimo, M., 2011. Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis Computer Speech and Language,
  • 2010

  • de Gispert, A., Iglesias, G., Blackwood, GW., Banga, ER. and Byrne, WJ., 2010. Hierarchical phrase-based translation with weighted finite state transducers and shallow-N grammars Computational Linguistics, v. 36
    Doi: http://doi.org/10.1162/coli_a_00006
  • 2008

  • Deng, Y. and Byrne, WJ., 2008. HMM word and phrase alignment for statistical machine translation IEEE Transactions on Audio Speech and Language Processing, v. 16
    Doi: http://doi.org/10.1109/TASL.2008.916056
  • 2007

  • Deng, Y., Kumar, S. and Byrne, W., 2007. Segmentation and alignment of parralel text for statistical machine translation Natural Language Engineering, v. 13
    Doi: http://doi.org/10.1017/S1351324906004293
  • Venkataramani, V., Chakrabartty, S. and Byrne, WJ., 2007. Ginisupport vector machines for segmental minimum Bayes risk decoding of continuous speech Computer Speech and Language, v. 21
    Doi: http://doi.org/10.1016/j.csl.2006.08.002
  • 2006

  • Li, J., Zheng, TF., Byrne, W. and Jurafsky, D., 2006. A dialectal Chinese speech recognition framework Journal of Computer Science and Technology, v. 21
    Doi: http://doi.org/10.1007/s11390-006-0106-9
  • Byrne, W., 2006. Minimum Bayes Risk Estimation and Decoding in Large Vocabulary Continuous Speech Recognition Proceedings of the Institute of Electronics, Information, and Communication Engineers, Japan – Special Section on Statistical Modeling for Speech Processing, v. E89-D
  • Kumar, S., Deng, Y. and Byrne, WJ., 2006. A weighted finite state transducer translation template model for statistical machine translation Journal of Natural Language Engineering, v. 12
    Doi: http://doi.org/10.1017/S1351324905003815
  • Doumpiotis, V. and Byrne, WJ., 2006. Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition Speech Communication, v. 48
    Doi: http://doi.org/10.1016/j.specom.2005.07.002
  • Li, J., Zheng, F., Byrne, WJ. and Jurafsky, D., 2006. A dialectal Chinese speech recognition framework Journal of Computer Science and Technology, v. 21
    Doi: http://doi.org/10.1007/s11390-006-0106-9
  • 2005

  • Gunawardana, A. and Byrne, WJ., 2005. Convergence theorems for generalized alternating minimization procedures Journal of Machine Learning Research, v. 6
  • Tsakalidis, S., Doumpiotis, V. and Byrne, WJ., 2005. Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation IEEE Transactions on Speech and Audio Processing, v. 1310
    Doi: http://doi.org/10.1109/TSA.2005.845806
  • 2004

  • Goel, V., Kumar, S. and Byrne, WJ., 2004. Segmental minimum Bayes-risk decoding for automatic speech recognition IEEE Transactions on Speech and Audio Processing, v. 12
    Doi: http://doi.org/10.1109/TSA.2004.825678
  • Byrne, WJ., Doermann, D., Franz, M., Gustman, S., Hajic, J., Oard, D., Picheny, M., Psutka, J., Ramabhadran, B., Soergel, D., Ward, T. and Wei Jing, Z., 2004. Automatic recognition of spontaneous speech for access to multilingual oral history archives IEEE Transactions on Speech and Audio Processing, v. 12
    Doi: http://doi.org/10.1109/TSA.2004.828702
  • 2002

  • Zheng, F., Song, Z., Fung, P. and Byrne, WJ., 2002. Mandarin pronunciation modeling based on CASS corpus Journal of Computer Science and Technology, v. 17
    Doi: http://doi.org/10.1007/BF02947304
  • 2001

  • Gunawardana, A. and Byrne, WJ., 2001. Discounted likelihood linear regression for rapid speaker adaptation Computer Speech and Language, v. 15
    Doi: http://doi.org/10.1006/csla.2000.0151
  • 2000

  • Byrne, WJ. and Gabai, A., 2000. Comments on "Efficient training algorithms for HMM's using incremental estimation" IEEE Transactions on Speech and Audio Processing, v. 8
    Doi: http://doi.org/10.1109/89.876315
  • Goel, V. and Byrne, WJ., 2000. Minimum Bayes-risk automatic speech recognition Computer Speech and Language, v. 14
    Doi: http://doi.org/10.1006/csla.2000.0138
  • 1999

  • Riley, M., Byrne, W., Finke, M., Khudanpur, S., Ljolje, A., McDonough, J., Nock, H., Saraclar, M., Wooters, C. and Zavaliagkos, G., 1999. Stochastic pronunciation modelling from hand-labelled phonetic corpora Speech Communication, v. 29
    Doi: http://doi.org/10.1016/S0167-6393(99)00037-0
  • 1994

  • Young, SJ., Woodland, PC. and Byrne, WJ., 1994. Spontaneous speech recognition for the credit card corpus using the HTK toolkit IEEE Transactions on Speech and Audio Processing, v. 2
    Doi: http://doi.org/10.1109/89.326619
  • 1992

  • Byrne, WJ., 1992. Alternating minimization and Boltzmann machine learning IEEE Transactions on Neural Networks, v. 3
    Doi: http://doi.org/10.1109/72.143375
  • 1986

  • Byrne, WJ., Zapp, R., Flynn, P. and Siegel, M., 1986. Adaptive filter processing in microwave remote heart monitors IEEE Transactions on Biomedical Engineering, v. 33
    Doi: http://doi.org/10.1109/TBME.1986.325763
  • Book chapters

    2010

  • Kurimo, M., Virpioja, S., Turunen, VT., Blackwood, GW. and Byrne, WJ., 2010. Overview and results of Morpho Challenge 2009
  • 2003

  • Goel, V. and Byrne, WJ., 2003. Minimum Bayes-risk automatic speech recognition
  • 1997

  • Byrne, W. and Sharma, S., 1997. Neurocontrol in sequence recognition
  • Reports

    2006

  • Venkataramani, V. and Byrne, WJ., 2006. Sub-problem selection for acoustic code-breaking
  • Other publications

    1993

  • Young, SJ., Woodland, PC. and Byrne, WJ., 1993. HTK V1.5: User, Reference and Programmer Manuals
  • Professor of Information Engineering
    Departments and institutes: 
    Professor Bill  Byrne

    Affiliations

    Classifications: