Acoustic speech recognition method and system using stereo...

Details Acoustic speech recognition method and system using stereo... Acoustic speech recognition method and system using stereo...

2005-09-20

2005-09-20

Dorvil, Richemond (Department: 2654)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S239000, C706S020000

Reexamination Certificate

active

06947890

ABSTRACT:
A method and system are provided for speech recognition. The speech recognition method includes the steps of preparing training data representing acoustic parameters of each of phonemes at each time frame; receiving an input signal representing a sound to be recognized and converting the input signal to input data; comparing the input data at each frame with the training data of each of the phonemes to derive a similarity measure of the input data with respect to each of the phonemes; and processing the similarity measures obtained in the comparing step using a neural net model governing development of activities of plural cells to conduct speech recognition of the input signal. In the processing step, each cell is associated with one respective phoneme and one frame, a development of the activity of each cell at each frame in the neural net model is suppressed by the activities of other cells on the same frame corresponding to different phonemes, and the development of the activity of each cell at each frame being enhanced by the activities of other cells corresponding to the same phoneme at different frames. In the process, the phoneme of a cell that has developed the highest activity is determined as a winner at the corresponding frame to produce a list of winners at respective frames. A phoneme is outputted as a recognition result for the input signal in accordance with the list of the winners at the respective frames that have been determined in the step of processing.

REFERENCES:
patent: 4975961 (1990-12-01), Sakoe
patent: 5059814 (1991-10-01), Mead et al.
patent: 5175793 (1992-12-01), Sakamoto et al.
patent: 5410635 (1995-04-01), Sakoe
patent: 5638486 (1997-06-01), Wang et al.
patent: 5809461 (1998-09-01), Inazumi
patent: 5933807 (1999-08-01), Fukuzawa
patent: 5960391 (1999-09-01), Tateishi et al.
patent: 6041299 (2000-03-01), Schuster et al.
patent: 6125345 (2000-09-01), Modi et al.
patent: 6151592 (2000-11-01), Inazumi
Maren et al., “A multilayer cooperative/competitive method for creating hierarchical structures by clustering maximally-related nodes,” IEEE International Conference on Neural Networks, Jul. 1988, vol. 2, pp. 95 to 105.
T. Kitzazoe, et al.,Sequential Stereoscopic Vision and Hysteresis, Proc. of Fifth Int. Conf. on Neural Information Processing, pp. 391-396, 1998.
D. Reinmann et al.,Stereo Vision by Self-organization, Biol. Cybern, vol.71, pp. 17-26, 1994.
Y. Yoshitomi, et al.,Neurol Nets Pattern Recognition Equation for Stereoscopic Vision, Trans. IPS, Japan, pp. 29-38, 1998.
S. NakagawaAbility and Limitation of Statistical Language Model, Proc. of ASJ, Japan, pp. 23-26, 1998.
R. Lippmann,An Introduction to Computing with Neural Nets, IEEE ASSP Mag., 4(2), pp 4-22, 1987.
T. Kitazoe et al.,Acoustic Speech Recognition Model by Neural Nets Equation with Competition and Cooperation, Transactions of the Technical Committee on Psychological and Physiological Acoustics, H-98-63 Acoustical Society of Japan, pp. 1-6, Tech. Rep. IEICD. SP98-45, Jul. 17, 1998.
T. Kitazoe et al.,Acoustic Speech Recognition Model by Neural Net Equation with Competition and Cooperation, Proc. of Fifth Int. Conference. on Spoken Language Processing, vol. 7, pp. 3281-3284, Nov. 30-Dec. 4, 1998.
T. Kitazoe et al.,Speech Recognition using Stereovision Neural Network Model, Proc. of The Fourth Int. Symp. on Artificial Life and Robotics (AROB 4th '99), Oita, Japan, pp. 576-579, Jan. 19-22, 1999.
T. Kitazoe et al.,Neural Net Equations with Competition and Cooperation for Speech Recognition, Information Processing Society of Japan, SIG NOtes SLP 25-5, pp. 25-30, Feb. 5, 1999.
T. Kitazoe et al.,Application of Stereovision Neural Network to Continuous Speech Recognition, Proc. of The Int. Symp. on Artificial Life an Robotics (AROB 5th'00), Oita Japan, 26-28, pp. 137-140, Jan. 2000.
T. Kitazoe, et al.,Acoustic Speech Recognition by Two and Three Layered Neural Networks with Competition and Cooperation, Proc. of SPECOM '99, Int. Workshop, Speech and Computer, Moscow, pp. 111-114, Oct. 4-7, 1999.
Amari, S. et al.,Competition and Cooperation in Neural Nets, Systems Neuroscience pp. 119-165, Academic Press, 1977.

Affiliated with

Also associated with

Rating

Acoustic speech recognition method and system using stereo... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Acoustic speech recognition method and system using stereo..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Acoustic speech recognition method and system using stereo... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3423511