Pattern matching for large vocabulary speech recognition...

Details Pattern matching for large vocabulary speech recognition... Pattern matching for large vocabulary speech recognition...

2005-04-12

2005-04-12

Dorvil, Richemond (Department: 2654)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S231000, C704S243000, C704S254000, C712S001000

Reexamination Certificate

active

06879954

ABSTRACT:
A method is provided for improving pattern matching in a speech recognition system having a plurality of acoustic models. The improved method includes: receiving continuous speech input; generating a sequence of acoustic feature vectors that represent temporal and spectral behavior of the speech input; loading a first group of acoustic feature vectors from the sequence of acoustic feature vectors into a memory workspace accessible to a processor; loading an acoustic model from the plurality of acoustic models into the memory workspace; and determining a similarity measure for each acoustic feature vector of the first group of acoustic feature vectors in relation to the acoustic model. Prior to retrieving another group of acoustic feature vectors, similarity measures are computed for the first group of acoustic feature vectors in relation to each of the acoustic models employed by the speech recognition system. In this way, the improved method reduces the number I/O operations associated with loading and unloading each acoustic model into memory.

REFERENCES:
patent: 5459798 (1995-10-01), Bailey et al.
patent: 6249761 (2001-06-01), Phillips et al.
patent: 6526380 (2003-02-01), Thelen et al.
patent: 20010041978 (2001-11-01), Crespo et al.
Gold, B., “Speech and Audio Signal Processing,” 2000, John Wiley & Sons, Inc. pp. 103-110.*
Ravishankar, M., “Efficient Algorithms for Speech Recognition,” May 1996, School of Computer Science, Carnegie Mellon University (CMU-CS-96-143), pp. 93.*
Lee et al., “A Fully Parallel Mandarin Speech Recognition System with Very Large Vocabulary and Almost Unlimited Texts,” Jun. 1991, International Symposium on Circuits and System, IEEE, Jun. 1991, pp. 578-581.*
Mitchell et al., “A Parallel Implementation of a Hidden Markov Model with Duration Modeling for Speech Recognition,” Jan. 1995, Digital Signal Processing, A Review Journal, 5(1).

Affiliated with

Also associated with

Rating

Pattern matching for large vocabulary speech recognition... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Pattern matching for large vocabulary speech recognition..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern matching for large vocabulary speech recognition... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3412875