Professor of Information Engineering
Statistical modelling for speech and language processing
Statistical machine translation
Departments and Institutes
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.
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.