Determining and using acoustic confusability, acoustic...

Details Determining and using acoustic confusability, acoustic... Determining and using acoustic confusability, acoustic...

2007-05-15

2007-05-15

Knight, Anthony (Department: 2121)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C703S002000, C704S236000, C704S246000, C704S251000

Reexamination Certificate

active

09838449

ABSTRACT:
Two statistics are disclosed for determining the quality of language models. These statistics are called acoustic perplexity and the synthetic acoustic word error rate (SAWER), and they depend upon methods for computing the acoustic confusability of words. It is possible to substitute models of acoustic data in place of real acoustic data in order to determine acoustic confusability. An evaluation model is created, a synthesizer model is created, and a matrix is determined from the evaluation and synthesizer models. Each of the evaluation and synthesizer models is a hidden Markov model. Once the matrix is determined, a confusability calculation may be performed. Different methods are used to determine synthetic likelihoods. The confusability may be normalized and smoothed and methods are disclosed that increase the speed of performing the matrix inversion and the confusability calculation. A method for caching and reusing computations for similar words is disclosed. Acoustic perplexity and SAWER are determined and applied.

REFERENCES:
patent: 4433210 (1984-02-01), Ostrowski et al.
patent: 4707858 (1987-11-01), Fette
patent: 4817156 (1989-03-01), Bahl et al.
patent: 5230037 (1993-07-01), Giustiniani et al.
patent: 5806029 (1998-09-01), Buhrke et al.
patent: 6073099 (2000-06-01), Sabourin et al.
patent: 6185530 (2001-02-01), Ittycheriah et al.
patent: 6263308 (2001-07-01), Heckerman et al.
patent: 6314399 (2001-11-01), Deligne et al.
patent: 6343270 (2002-01-01), Bahl et al.
patent: 6366885 (2002-04-01), Basu et al.
patent: 6671668 (2003-12-01), Harris
patent: 6701162 (2004-03-01), Everett
patent: 6718303 (2004-04-01), Tang et al.
Gravier et al, “Directory Name Retrieval Using HMM Modeling and Robust Lexical Access”, Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on , Dec. 14-17, 1997 pp. 558-565.
Stolcke, Andreas, “An Efficient Probabilistic Context-free Parsing Algorithm that Computes Prefix Probabilities”, Computational Linguistics, vol. 21, Issue 2, Jun. 1995, pp. 165-201.
Bahl et al, “Constructing Groups of Acoustically Confusable Words”, Acoustics, Speech, and Signal Processing, 1990. ICASSP-90, 1990, International Conference on, Apr. 3-6, 1990, pp. 85-88 vol. 1.
Jelinek, F., “Self-organized Language Modeling for Speech Recognition”, Readings in Speech Recognition, p. 474, 1990.
Bahl et al., “A Maximum Likelihood Approach to Continuous Speech Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-5, No. 2, pp. 179-190 (Mar. 1983).
Clarkson et al., “The Applicability of Adaptive Language Modelling for the Broadcast News Task,” Proceedings of the Fifth International Conference on Spoken Language Processing, Sydney, Australia, p. 2 (Nov. 1998).
Gopalakrishnan et al., “An Inequality for Rational Functions with Applications to Some Statistical Estimation Problems,” IEEE Transactions on Information Theory, vol. 37, No. 1, pp. 107-113 (Jan. 1991).
Jelinek, F., “Statistical Methods for Speech Recognition,” The MIT Press, Cambridge, MA, Sec. 8.3 re perplexity, p. 2 (1999).
Printz et al., “Theory and Practice of Acoustic Confusability,” Proceedings of the ISCA ITRW ASR2000, pp. 77-84 (Sep. 18-20, 2000).

Affiliated with

Also associated with

Rating

Determining and using acoustic confusability, acoustic... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Determining and using acoustic confusability, acoustic..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Determining and using acoustic confusability, acoustic... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3778995