Reducing computation on parallel decoding using frame-wise confidence scores
暂无分享,去创建一个
Yoshihiko Nankaku | Keiichi Tokuda | Akinobu Lee | Tomohiro Hakamata | K. Tokuda | Yoshihiko Nankaku | Akinobu Lee | T. Hakamata
[1] Kiyohiro Shikano,et al. Recent progress of open-source LVCSR engine julius and Japanese model repository , 2004, INTERSPEECH.
[2] Kiyohiro Shikano,et al. Real-time word confidence scoring using local posterior probabilities on tree trellis search , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.
[3] Takehito Utsuro,et al. Evaluating multiple LVCSR model combination in NTCIR-3 speech-driven web retrieval task , 2003, INTERSPEECH.
[4] Jian Liu,et al. A dynamic cross-reference pruning strategy for multiple feature fusion at decoder run time , 2003, INTERSPEECH.
[5] Kiyohiro Shikano,et al. Continuous Speech Recognition Consortium an Open Repository for CSR Tools and Models , 2002, LREC.
[6] Timothy J. Hazen,et al. Word and phone level acoustic confidence scoring , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).
[7] Jonathan G. Fiscus,et al. A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.
[8] Sadaoki Furui,et al. Spontaneous speech recognition using a massively parallel decoder , 2004, INTERSPEECH.