A confidence-guided dynamic pruning approach - utilization of confidence measurement in speech recognition

An improved system for recording and playing back digital information in a special pulse-length modulation format on a disc-shaped record. The digital information is stored in a succession of alternating marks and spaces, both having lengths that are discretely variable in accordance with a succession of multi-bit binary code blocks.

[1]  Hermann Ney,et al.  Look-ahead techniques for fast beam search , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[2]  Thomas Bub,et al.  VERBMOBIL: the evolution of a complex large speech-to-speech translation system , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[3]  Feng Liu,et al.  A new verification-based fast match approach to large vocabulary speech recognition , 2001, INTERSPEECH.

[4]  Günther Ruske,et al.  Impact of word graph density on the quality of posterior probability based confidence measures , 2003, INTERSPEECH.

[5]  Steve Renals,et al.  Confidence measures for hybrid HMM/ANN speech recognition , 1997, EUROSPEECH.

[6]  Sherif Abdou,et al.  An efficient, fast matching approach using posterior probability estimates in speech recognition , 2003, INTERSPEECH.

[7]  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).

[8]  Steve Renals,et al.  Start-synchronous search for large vocabulary continuous speech recognition , 1999, IEEE Trans. Speech Audio Process..

[9]  Hugo Van hamme,et al.  An adaptive-beam pruning technique for continuous speech recognition , 1996, ICSLP.

[10]  Steve Young,et al.  The HTK hidden Markov model toolkit: design and philosophy , 1993 .