Apparatus for calculating a posterior probability of phoneme sym

Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

706 25, 706 42, G10L 506

Patent

active

060412992

ABSTRACT:
There are disclosed an apparatus for calculating a posteriori probabilities of phoneme symbols and a speech recognition apparatus using the apparatus for calculating a posteriori probabilities of phoneme symbols. A feature extracting section extracts speech feature parameters from a speech signal of an uttered speech sentence composed of an inputted character series, and a calculating section calculates a a posteriori probability of a phoneme symbol of the speech signal, by using a bidirectional recurrent neural network. The bidirectional recurrent neural network includes (a) an input layer for receiving the speech feature parameters extracted by the feature extracting means and a plurality of hypothetical phoneme symbol series signals, (b) an intermediate layer of at least one layer having a plurality of units, and (c) an output layer for outputting a a posteriori probability of each phoneme symbol. The input layer includes (a) a first input neuron group having a plurality of units, for receiving a plurality of speech feature parameters and a plurality of phoneme symbol series signals, (b) a forward module, and (c) a backward module.

REFERENCES:
patent: 5408424 (1995-04-01), Lo
patent: 5748848 (1998-05-01), Tresp
patent: 5956702 (1999-09-01), Matsuoka et al.
Abrash, "Mixture Input Transformations for Adaptation of Hybrid Connectionist Speech Recognizers", 5.sup.th European Conf. of Speech Commo. and Technology, Rhodes, Greece, pp. 1-4, 1997.
Mike Schuster, et al., "Bidirectional Recurrent Neural Networks" Nov. 1997, IEEE Transactions On Signal Processing, vol. 45, No. 11, pp. 2673-2681.
M. Schuster, "Learning Out of Time Series With an Extended Recurrent Neural Network", Neural Networks for Signal Processing VI, Proceedings of the 1996 IEEE Signal Processing Society Workshop, (Cat. No. 96TH8205) Neural Networks for Signal Processing Society Workshop, Kyoto, Japan, 4-6, pp. 170-179.
A. Robinson, et al. "An Application of Recurrent Nets to Phone Probability Estimation", IEEE Transaction on Neural Networks, vol. 5, No. 2, Mar. 1, 1994, pp. 298-305.
R. Allen, "A Recurrent Neural Network for Word Identification From Phoneme Sequences", Proceedings of the International Conference on Spoken Language Processing, KOBE, Nov. 18-22, 1990, pp. 1037-1040.
J. Bridle, "Alpha-nets: A Recurrent `Neural` Network Architecture With A Hidden Mark Model Interpretation", Speech Communication, vol. 9, No. 1, Feb. 1, 1990, pp. 83-92.
Anthony J. Robinson, "An Application of Recurrent Nets to Phone Probability Estimation"; IEEE Transactions on Neural Networks; vol. 5, No. 2, Mar. 1994; pp. 298-305.
Herve Bourlard, "Continuous Speech Recognition by Connectionist Statistical Methods"; IEEE Transactions on Neural Networks; vol. 4, No. 6, Nov. 1993; pp. 893-909.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Apparatus for calculating a posterior probability of phoneme sym does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Apparatus for calculating a posterior probability of phoneme sym, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Apparatus for calculating a posterior probability of phoneme sym will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-738010

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.