| Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. X Chen, T Tan, X Liu, P Lanchantin, M Wan, MJF Gales, PC Woodland INTERSPEECH 15, 3511-3515, 2015 | 114 | 2015 |
| Distributed inference for Dirichlet process mixture models H Ge, Y Chen, M Wan, Z Ghahramani International Conference on Machine Learning, 2276-2284, 2015 | 47 | 2015 |
| Integrated speaker-adaptive speech synthesis M Wan, G Degottex, MJF Gales | 10* | |
| Waveform-based speaker representations for speech synthesis M Wan, G Degottex, MJF Gales ISCA, 2018 | 3 | 2018 |
| Deliberation-Based Multi-Pass Speech Synthesis Q Dou, X Wu, M Wan, Y Lu, MJF Gales Proc. Interspeech 2021, 136-140, 2021 | 2 | 2021 |
| Hierarchical rnns for waveform-level speech synthesis Q Dou, M Wan, G Degottex, Z Ma, MJF Gales 2018 IEEE Spoken Language Technology Workshop (SLT), 618-625, 2018 | 2 | 2018 |
Yutian ChenResearch Scientist, DeepMindVerified email at google.com
