Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2003-02-12
2010-11-02
Hudspeth, David R (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S202000, C704S231000, C704S251000, C704S252000, C704S255000, C704S256000, C700S048000, C706S015000
Reexamination Certificate
active
07827031
ABSTRACT:
A neural network in a speech-recognition system has computing units organized in levels including at least one hidden level and one output level. The computing units of the hidden level are connected to the computing units of the output level via weighted connections, and the computing units of the output level correspond to acoustic-phonetic units of the general vocabulary. This network executes the following steps:determining a subset of acoustic-phonetic units necessary for recognizing all the words contained in the general vocabulary subset;eliminating from the neural network all the weighted connections afferent to computing units of the output level that correspond to acoustic-phonetic units not contained in the previously determined subset of acoustic-phonetic units, thus obtaining a compacted neural network optimized for recognition of the words contained in the general vocabulary subset; andexecuting, at each moment in time, only the compacted neural network.
REFERENCES:
patent: 5461696 (1995-10-01), Frank et al.
patent: 5621859 (1997-04-01), Schwartz et al.
patent: 5638487 (1997-06-01), Chigier
patent: 5745649 (1998-04-01), Lubensky
patent: 5822742 (1998-10-01), Alkon et al.
patent: 5867816 (1999-02-01), Nussbaum
patent: 5960391 (1999-09-01), Tateishi et al.
patent: 6151592 (2000-11-01), Inazumi
patent: 6208963 (2001-03-01), Martinez et al.
patent: 6240389 (2001-05-01), Keiller et al.
patent: 6665639 (2003-12-01), Mozer et al.
patent: 6832191 (2004-12-01), Frasca et al.
patent: 0 623 914 (1994-11-01), None
patent: 0 733 982 (1996-09-01), None
Albesano, D., Gemello, R., Mana, F., 1997. Hybrid HMM-NN modeling of stationary-transitional units for continuous speech recognition. In: Proc. Neural Information Processing, pp. 1112-1115.
Sietsma, J., Dow, R.J.F., 1988. Neural net pruning—why and how. In IEEE International Conference on Neural Networks 1 (San Diego, 1988). IEEE, New York, pp. 325-333.
Abdallah, Moatassem M. et al. “A modular neural network approach to the speech recognition problem” in: ANNIE '99, pp. 1079-1083.
Albesano, D., Baggia, P., Danieli, M., Gemello, R., Gerbino, E., and Rullent, C. (1997). A robust sys-tem for human-machine dialogue in a telephony-based application. Journal of Speech Technology,2(2), 99-110.
Pruning Algorithms—A Survey by Russel Reed (IEEE Sep. 1993).
A Whole Wordrecurrent Neural Network . . . by Naylor et al. (IEEE Sep. 1992).
Albesano Dario
Gemello Roberto
Banner & Witcoff , Ltd.
Hudspeth David R
Loquendo S.p.A.
Shah Paras
LandOfFree
Method for accelerating the execution of speech recognition... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for accelerating the execution of speech recognition..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for accelerating the execution of speech recognition... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4251873