Patent
1996-11-19
1998-01-13
Knepper, David D.
395 244, 395 22, 395 222, 395 254, 395 253, 395 261, G10L 500, G10L 506, G10L 912
Patent
active
057087598
ABSTRACT:
A method and apparatus for computer speech recognition based on time-domain phoneme waveform identification. In Mainwave-Ripple Model (MRM) analysis, the waveform is located in a short interval called a frame, and waveform structural features are located and measured, to form a waveform analysis array in terms of fine-structure parameters and main-structure parameters. Analysis can also derive multi-frame pattern analysis arrays. In training mode, phoneme reference arrays are formed by combining a known most-probable analysis array with its corresponding phoneme symbol. In recognition mode, unknown input signal analysis arrays are compared with prestored reference arrays, whereby a best-match recognition is made. Selectable levels of processing provide selectable speed versus accuracy, in terms of protowave, phonode, or phoneme recognition. A computer program storage device readable by a computer system for implementing the method is included.
REFERENCES:
patent: 3553372 (1971-01-01), Wright et al.
patent: 4559602 (1985-12-01), Bates, Jr.
patent: 4661915 (1987-04-01), Ott
patent: 4692941 (1987-09-01), Jacks et al.
patent: 4882757 (1989-11-01), Fisher et al.
patent: 5359695 (1994-10-01), Ohora et al.
patent: 5388182 (1995-02-01), Benedetto et al.
patent: 5495554 (1996-02-01), Edwards et al.
patent: 5528725 (1996-06-01), Hui
T.W. Parson, Voice and Speech Processing, McGraw-Hill Book. Co. 1986. pp. 170,171,208,209,291.
W. J. Hess IEEE Trans. on Acoustics, etc. vol. ASSP-24, No. 1, A Pitch-Synchronous Digital Feature Extraction System for Phoneme Recognition of Speech, Feb., 1976. pp. 14-25.
Peking Faculty, Modern Chinese, Dover Press, 1971. pp. 4,5.
Long & Datta, "Wavelet Based Feature Extraction for Phoneme Recognition", ICSLP96 Oct. 1996, pp. 1-4.
Tan, Fu & Spray, "The Use of Wavelet Transforms in Phoneme Recognition", ICSLP96, Oct. 1996, pp. 1-4.
Matthews, Bangham & Cox, "Audiovisual Speech Recognition Using Multiscale Nonlinear Image Decomposition", ICSLP '96, Oct. 1996, pp. 1-14.
Mallat & Zhong, "Wavelet Transform Maxima and Multiscale Edges", Wavelets and Their Applications, Jones & Bartlett, Boston, 1992, pp. 67-104.
LandOfFree
Speech recognition using phoneme waveform parameters 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 recognition using phoneme waveform parameters, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition using phoneme waveform parameters will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-332580