1993-07-14
1994-09-06
Knepper, David D.
395 249, G01L 708, G01L 918
Patent
active
053455355
ABSTRACT:
System (100) receives a speech signal at an input (102) which is measured and transformed by speech feature measuring device (104). The output feature vector from speech feature measuring device (104) is then compared to a reference model in a statistical classification manner. Acoustic similarity measuring device (106) performs statistical measurements while temporal speech model constraints block (108) imposes transitional probabilities to the probability measurements generated by measuring device (106). Acoustic similarity measuring device (106) performs a weighted analysis of the error vector defined between the speech feature vector and reference vector utilized during the analysis.
REFERENCES:
patent: 4032711 (1977-06-01), Sambur
patent: 4669120 (1987-05-01), Ono
patent: 4716592 (1987-12-01), Ozawa et al.
patent: 4724535 (1988-02-01), Ono
patent: 4741036 (1988-04-01), Bahl et al.
patent: 5072452 (1991-12-01), Brown et al.
Nahamoo, Clustering Acoustic Prototypes With Self Organizing Distortion Measures, Apr. 7, 1986, vol. 1, Int'l Conf. on Acoustics Speech & Signal Processing, Tokyo, Japan, pp. 753-754.
Class, et al., Speaker Adaptation for Recognition Systems With a Large Vocabulary, Apr. 11, 1989, Mediterranean Electrotechnical Conf. Melecon' 89, Lisbon, Sec. 2.1, 2.3, pp. 241-243.
Wang, Ren-Hua, et al., A Weighted Distance Measure Based on the Fine Structure of Feature Space: Application to Speaker Recognition, Apr. 3, 1990, vol. 1, Int'l Conf. on Acoustics Speech & Signal Processing, Albuquerque, N. Mex., USA, pp. 273-276 (Sec. 2-pp. 273-274).
Velius, G., Variants of Cepstrum Based Speaker Identity Verification, Apr. 11, 1988, vol. 1, Int'l Conf. on Acoustics Speech & Signal Processing, New York, USA, pp. 583-586 (Sec. 5,6-pp. 584-585).
Tohkura, A Weighted Cepstral Distance Measure for Speech Recognition, Apr. 7, 1989, vol. 1, Int'l Conf. on Acoustics Speech & Signal Processing, Tokyo, Japan, pp. 761-764 (Sec. 2, 3.3, Exp. II, III).
Lleida, et al., Feature Selection Through Orthogonal Expansion in Isolated Word Recognition, Apr. 11, 1989, Mediterranean Electrotechnical Conf. Melecon 89, Lisbon, Sec. 2, p. 254.
IEEE "A Weighted Cepstral Distance Measure for Speech Recognition" (Apr., 1986, pp. 761-764) by Yoh ichi Tohkura.
IEEE "On The Use of Bandpass Liftering in Speech Recognition" (Apr., 1986, pp. 765-768) by B. H. Juang, L. R. Rabiner and J. G. Wilpon.
IEEE "A Frequency-Weighted Itakura Spectral Distortion Measure and Its Application To Speech Recognition in Noise" (Jan., 1988, pp. 41-48) by Frank K. Soong and Man Mohan Sondhi.
IEEE "A Comparative Study of Cepstcal Lifters and Distance Measures For All Pole Models of Speech Noise" (Feb., 1989 pp. 476-479) by Jean-Claude Junqua and Hisashi Wakita.
Hataoka et al., "VCV Segmentation and Phoneme Recognition in Continuous Speech," IEEE ICASSP 86, Tokyo, 1986, pp. 2299-2302.
Donaldson Richard L.
Knepper David D.
Troike Robert L.
LandOfFree
Speech analysis method and apparatus does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Speech analysis method and apparatus, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech analysis method and apparatus will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1335131