Patent
1995-06-05
1997-07-22
Sheikh, Ayaz R.
395 24, 395 245, 395 247, G01L 500
Patent
active
056510942
ABSTRACT:
Each time a matching unit 22 finishes a matching at a time "i" between feature vectors of input speech which have been converted by an analyzer 1 and feature vectors of reference patterns stored in a reference pattern memory 2, and goes to a matching at a next time "i+1", a feature vector integrator 24 multiplies the feature vectors of the input speech or the reference patterns by a weight w1 in each of acoustic categories, successively integrates products, stores integrated values in respective frames of the reference patterns in feature vector accumulating buffers 26, and integrates and stores weights w1 in feature vector weight counters 27 corresponding to the respective acoustic categories. When the feature vector integrator 24 finishes integrating and storing processes corresponding to the final matching process, a mean value calculator 28 divides the values stored in the final frames in the feature vector accumulating buffers 26 by the values stored in the feature vector weight counters 27, and outputs the quotients as mean values in the respective acoustic categories of the input speech or the reference patterns. An adaptation unit 55 adapts one or both of the input speech or the reference patterns using the mean values.
REFERENCES:
patent: 4530110 (1985-07-01), Nojiri et al.
patent: 4559604 (1985-12-01), Ichikawa et al.
patent: 4720802 (1988-01-01), Damoulakis et al.
patent: 4783802 (1988-11-01), Takebayashi et al.
patent: 5159637 (1992-10-01), Okazaki et al.
patent: 5274737 (1993-12-01), Shinoda
patent: 5315689 (1994-05-01), Kanazawa et al.
K. Shinoda et al., "Speaker Adaption Using Spectral Interpolation for Speech Recognition", Treatises A of Electronics, Information and Communication Engineers, vol. J77-A No. 2, pp. 120-127, Feb., 1994.
Takagi et al., "Speech Recognition with Environment Adaption by Spectrum Equaliztion", Collected Lecture Papers of Spring Meeting of the Acoustical Society of Japan, p. 173-174, Mar., 1994.
Shinoda et al; "Speaker Adaptation for demi-syllable based continous density HMM"; ICASSP 1991 pp. 857-860 Jul. 1991.
Takagi et al; "Rapid Environment adaptation for Robust Speech Recognition"; ICASSP May 1995; pp. 149-152 May 1995.
Hattori Hiroaki
Takagi Keizaburo
NEC Corporation
Opsasnick Michael
Sheikh Ayaz R.
LandOfFree
Acoustic category mean value calculating apparatus and adaptatio 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 category mean value calculating apparatus and adaptatio, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Acoustic category mean value calculating apparatus and adaptatio will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1565460