Patent
1995-09-20
1998-09-22
MacDonald, Allen R.
395 251, 395 249, G10L 302
Patent
active
058127399
ABSTRACT:
A euclidean distance between an input pattern and a reference pattern is elementwise determined, to sequentially calculate a set of cumulative values thereof, which is stored in a work memory for use in a current recurrence calculation and in a cumulative data memory for use in a decision for a speech recognition. The recurrence calculation is executed on one of division blocks obtained by collecting input frames and reference frames. Stored data in the work memory are shifted every block for a subsequent recurrence calculation.
REFERENCES:
patent: 3816722 (1974-06-01), Sakoe et al.
patent: 4587637 (1986-05-01), Ishizuka
patent: 4592086 (1986-05-01), Watari et al.
patent: 4868879 (1989-09-01), Morito
patent: 4910783 (1990-03-01), Nakagawa
patent: 5121465 (1992-06-01), Sakoe
patent: 5355432 (1994-10-01), Tanaka
patent: 5577162 (1996-11-01), Yamazaki
H. Sakoe et al., "A High Speed DP-Matching Algorithm . . . Quantization", Association of Electronic, Information and Communications Engineers of Japan, vol. J71-D, No. 9, Sep. 1988, pp. 1650-1659.
S. Nakagawa, "Speech Recognition by Probability Model", Association of Electronic, Information and Communications Engineers of Japan, Jul. 1988, pp. 29-50.
T. Furui, "Digital Speech Processing", Tokai University Publishing Company, pp. 154-155.
Chapman & Hall, Holmes, "Speech synthesis and recognition", capter 7, pp. 102-128, especially p. 103 section 7.2 1988.
Dorvic Richemond
MacDonald Allen R.
NEC Corporation
LandOfFree
Speech recognition system and speech recognition method with red 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 system and speech recognition method with red, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition system and speech recognition method with red will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1631896