| The Titech large vocabulary WFST speech recognition system PR Dixon, DA Caseiro, T Oonishi, S Furui 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU …, 2007 | 80 | 2007 |
| Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition PR Dixon, T Oonishi, S Furui Computer Speech & Language 23 (4), 510-526, 2009 | 67 | 2009 |
| Fast acoustic computations using graphics processors PR Dixon, T Oonishi, S Furui 2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009 | 61 | 2009 |
| Multimodal approach for avatar animation ASEDH ABDELAZIZ, N Apostoloff, J BINDER, PR DIXON, S Kajarekar, ... US Patent App. 16/723,866, 2021 | 55 | 2021 |
| TREC 2005 Question Answering Experiments at Tokyo Institute of Technology. EWD Whittaker, P Chatain, S Furui, D Klakow TREC, 2005 | 52 | 2005 |
| Improving WFST-based G2P Conversion with Alignment Constraints and RNNLM N-best Rescoring. JR Novak, N Minematsu, K Hirose, C Hori, H Kashioka, PR Dixon Interspeech, 2526-2529, 2012 | 50 | 2012 |
| Modality dropout for improved performance-driven talking faces A Hussen Abdelaziz, BJ Theobald, P Dixon, R Knothe, N Apostoloff, ... Proceedings of the 2020 International Conference on Multimodal Interaction …, 2020 | 41 | 2020 |
| Rescoring a phrase-based machine transliteration system with recurrent neural network language models A Finch, P Dixon, E Sumita Proceedings of the 4th Named Entity Workshop (NEWS) 2012, 47-51, 2012 | 23 | 2012 |
| Combining a two-step conditional random field model and a joint source channel model for machine transliteration D Yang, P Dixon, YC Pan, T Oonishi, M Nakamura, S Furui Proceedings of the 2009 Named Entities Workshop: Shared Task on …, 2009 | 23 | 2009 |
| Implementation and Evaluation of Fast On-the-fly WFST Composition T Oonishi, P Dixon, K Iwano, S Furui A: A 1, R1, 2008 | 22 | 2008 |
| The NICT ASR system for IWSLT2012 H Yamamoto, Y Wu, CL Huang, X Lu, P Dixon, S Matsuda, C Hori, ... Proceedings of the 9th International Workshop on Spoken Language Translation …, 2012 | 20 | 2012 |
| A specialized wfst approach for class models and dynamic vocabulary PR Dixon, C Hori, H Kashioka Proc. Interspeech 2012, 1075-1078, 2012 | 18 | 2012 |
| Investigation of the effects of ASR tuning on speech translation performance P Dixon, A Finch, C Hori, H Kashioka Proceedings of the 8th International Workshop on Spoken Language Translation …, 2011 | 17 | 2011 |
| A comparison of dynamic WFST decoding approaches PR Dixon, C Hori, H Kashioka 2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012 | 16 | 2012 |
| Flexible keyword spotting based on homogeneous audio-text embedding K Nishu, M Cho, P Dixon, D Naik ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 14 | 2024 |
| Development of the SprinTra WFST speech decoder PR Dixon, C Hori, H Kashioka Journal of the National Institute of Information and Communications …, 2012 | 14 | 2012 |
| Generalization of specialized on-the-fly composition T Oonishi, PR Dixon, K Iwano, S Furui 2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009 | 14 | 2009 |
| The nict asr system for iwslt 2013 CL Huang, P Dixon, S Matsuda, Y Wu, X Lu, M Saiko, C Hori Proceedings of the 10th International Workshop on Spoken Language …, 2013 | 13 | 2013 |
| Integrating models derived from non-parametric bayesian co-segmentation into a statistical machine transliteration system A Finch, P Dixon, E Sumita Proceedings of the 3rd Named Entities Workshop (NEWS 2011), 23-27, 2011 | 13 | 2011 |
| An Empirical Comparison of the T3, Juicer, HDecode and Sphinx3 Decoders JR Novak, PR Dixon, S Furui Eleventh Annual Conference of the International Speech Communication Association, 2010 | 13 | 2010 |
Tasuku OonishiVerified email at google.com
