Method and system for improving speech recognition through front

Details Method and system for improving speech recognition through front Method and system for improving speech recognition through front

1994-07-29

1997-02-18

MacDonald, Allen R.

395 233, G10L 900

Patent

active

056048394

ABSTRACT:
A method and system for improving speech recognition through front-end normalization of feature vectors are provided. Speech to be recognized is spoken into a microphone, amplified by an amplifier, and converted from an analog signal to a digital signal by an analog-to-digital ("A/D") converter. The digital signal from the A/D converter is input to a feature extractor that breaks down the signal into frames of speech and then extracts a feature vector from each of the frames. The feature vector is input to an input normalizer that normalizes the vector. The input normalizer normalizes the feature vector by computing a correction vector and subtracting the correction vector from the feature vector. The correction vector is computed based on the probability of the current frame of speech being noise and based on the average noise and speech feature vectors for a current utterance and a database of utterances. The normalization of the feature vector reduces the effect of changes in the acoustical environment on the feature vector. The normalized feature vector is input to a pattern matcher that compares the normalized vector to feature models stored in the database to find an exact match or a best match.

REFERENCES:
patent: 5185848 (1993-02-01), Aritsuka et al.
Acero, A. et al., "Robust HMM-Based Endpoint Detector," in Eurospeech '93 3rd European Conference on Speech Communication and Technology, Berlin, Germany, Sep. 21-23, 1993, pp. 1551-1554.
Liu, Fu-Hua et al., "Efficient Cepstral Normalization for Robust Speech Recognition," in Proceedings of a Human Language Technology Workshop, Advanced Research Projects Agency, Plainsboro, New Jersey, Mar. 21-24, 1993, pp. 69-74.
Acero, Alejandro, "Acoustical and Environmental Robustness in Automatic Speech Recognition," Dissertation, Carnegie Mellon University, Pittsburgh, Pennsylvania, Sep. 13, 1990, pp. i-xi, 1-141.
Acero, Alejandro, Acoustical and Environmental Robustness in Automatic Speech Recognition, Kluwer Academic Publishers, Boston, Massachusetts, 1993, pp. i-xvii, Forward, 1-186.
Dempster, A. P. et al., "Maximum Likelihood from Incomplete Data via the EM Algorithm," Journal of The Royal Statistical Society 39(1), 1977, pp. 1-38.
Sankar, Ananth and Chin-Hui Lee, "Stochastic Matching for Robust Speech Recognition," IEEE Signal Processing Letters 1(8), Aug. 1994, pp. 124-125.

Affiliated with

Also associated with

Rating

Method and system for improving speech recognition through front 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 and system for improving speech recognition through front, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for improving speech recognition through front will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1608192