Time synchronous decoding for long-span hidden trajectory model

Details Time synchronous decoding for long-span hidden trajectory model Time synchronous decoding for long-span hidden trajectory model

2011-01-25

2011-01-25

Dorvil, Richemond (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S231000, C704S242000

Reexamination Certificate

active

07877256

ABSTRACT:
A time-synchronous lattice-constrained search algorithm is developed and used to process a linguistic model of speech that has a long-contextual-span capability. In the algorithm, hypotheses are represented as traces that include an indication of a current frame, previous frames and future frames. Each frame can include an associated linguistic unit such as a phone or units that are derived from a phone. Additionally, pruning strategies can be applied to speed up the search. Further, word-ending recombination methods are developed to speed up the computation. These methods can effectively deal with an exponentially increased search space.

REFERENCES:
patent: 5129002 (1992-07-01), Tsuboka
patent: 5515475 (1996-05-01), Gupta et al.
patent: 5677988 (1997-10-01), Takami et al.
patent: 5706397 (1998-01-01), Chow
patent: 5787396 (1998-07-01), Komori et al.
patent: 6067520 (2000-05-01), Lee
patent: 6397179 (2002-05-01), Crespo et al.
patent: 6931374 (2005-08-01), Attias
patent: 7050975 (2006-05-01), Deng
patent: 7092883 (2006-08-01), Gretter et al.
patent: 7295980 (2007-11-01), Garner et al.
patent: 7319960 (2008-01-01), Riis et al.
patent: 7464033 (2008-12-01), Gong
patent: 2002/0048350 (2002-04-01), Phillips et al.
patent: 2005/0149326 (2005-07-01), Hogengout et al.
patent: 2005/0267751 (2005-12-01), Bangalore et al.
patent: 2006/0074676 (2006-04-01), Deng
patent: 2006/0100862 (2006-05-01), Deng
patent: 2006/0200351 (2006-09-01), Acero
patent: 2007/0143104 (2007-06-01), Deng
Jian-Lai Zhou; Seide, F.; Li Deng, “Coarticulation modeling by embedding a target-directed hidden trajectory model into HMM—model and training,” Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on , vol. 1, no., pp. I-744-I-747 vol. 1, Apr. 6-10, 2003.
Kirchhoff, “Robust Speech Recognition Using Articulatory Information,” PhD thesis, University of Bielefeld, Germany, Jul. 1999, pp. 1-136.
U.S. Appl. No. 11/093,833, filed Oct. 12, 2006, Acero et al.
U.S. Appl. No. 11/356,905, filed Aug. 23, 2007, Li et al.
L. Deng, X. Li, D. Yu and A. Acero, “A Hidden Trajectory Model with Bi-directional Target-Filtering: Cascaded vs. Integrated Implementation for Phonetic Recognition” Proc. of ICASSP, pp. 337-340, Philidelphia, PA, USA 2005.
D. Yu, L. Deng and A. Acero, “Evaluation of a Long-contextual-span Hidden Trajectory Model and Phonetic Recognizer Using A* Lattice Search”, Proc. of Eurospeech, Lisboa, Sep. 2005.
L. Deng, D. Yu, X. Li, and A. Acero “A long-contextual-span Model of Resonance Dynamics for Speech Recognition: Parameter Learning and Recognizer Evaluation” accepted into IEEE Workshop on Automatic Speech Recognition & Understanding, Cancun, Mexico, Nov. 2005.
H. Ney, S. Ortmanns, “Dynamic programming search for continuous speech recognition” IEEE Signal Processing Magazine, 16 (5), pp. 64-83, 1999.
A. Sixtus, Crossword Phoneme Models for Large Vocabulary Continuous Speech Recognition PhD. Dissertation, RWTH, Germany, 2003.
D. B. Wagner, “Dynamic Programming,” The Mathematica Journal, vol. 5., issue 4, pp. 42-51 (1995).
L. Deng, D. Yu, and A. Acero. “A quantitative model for formant dynamics and contextually assimilated reduction in fluent speech”, in Proc. ICSLP, pp. 719-722, Jeju, Korea, 2004.
L. Deng, D. Yu, and A. Acero. “Learning statistically characterized resonance targets in a hidden trajectory model of speech coarticulation and reduction”, in Proc. Interspeech 2005, Lisbon, Sep. 2005, pp. 1097-1100.
M. Akagi. “Modeling of contextual effects based on spectral peak interaction,” in J. Acoust. Soc. Am., vol. 93, No. 2, pp. 1076-1086, 1993.
J. Glass. “A probabilistic framework for segment-based speech recognition,” in Computer Speech and Language, vol. 17, 2003, pp. 137-152.
J. Krause and L. Braida. “Acoustic properties of naturally produced clear speech at normal speaking rates,” in J. Acoust. Soc. Am., vol. 115, No. 1, pp. 362-378, 2004.
S. Ortmanns, A. Eiden, H. Ney and N. Coenen, “Look-ahead Techniques for Fast Beam Search” Proc. of ICASSP, pp. 1783-1786, Munich, Germany 1997.
B-H Tran, V. Steinbiss and H. Ney, “Improvements in beam search” In Proc. of ICSLP, pp. 2143-2146, 1994.

Affiliated with

Also associated with

Rating

Time synchronous decoding for long-span hidden trajectory model does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Time synchronous decoding for long-span hidden trajectory model, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Time synchronous decoding for long-span hidden trajectory model will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2633071