Standard-model generation for speech recognition using a...

Details Standard-model generation for speech recognition using a... Standard-model generation for speech recognition using a...

2003-11-18

2009-10-13

Dorvil, Richemond (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S243000, C704S256000

Reexamination Certificate

active

07603276

ABSTRACT:
A standard model creating apparatus which provides a high-precision standard model used for pattern recognition such as speech recognition, character recognition, or image recognition using a probability model based on a hidden Markov model, Bayesian theory, or linear discrimination analysis; intention interpretation using a probability model such as a Bayesian net; data-mining performed using a probability model; and so forth. The standard model creating apparatus includes a reference model preparing unit that prepares at least one reference model; a reference model storing unit that stores the reference model prepared by the reference model preparing unit; and a standard model creating unit that creates a standard model by calculating statistics of the standard model so as to maximize or locally maximize the probability or likelihood with respect to the reference model stored in the reference storing unit.

REFERENCES:
patent: 4587670 (1986-05-01), Levinson et al.
patent: 5450523 (1995-09-01), Zhao
patent: 5488652 (1996-01-01), Bielby et al.
patent: 5684924 (1997-11-01), Stanley et al.
patent: 5825978 (1998-10-01), Digalakis et al.
patent: 5850627 (1998-12-01), Gould et al.
patent: 5895447 (1999-04-01), Ittycheriah et al.
patent: 6038535 (2000-03-01), Campbell
patent: 6253181 (2001-06-01), Junqua
patent: 6263309 (2001-07-01), Nguyen et al.
patent: 6430551 (2002-08-01), Thelen et al.
patent: 6442519 (2002-08-01), Kanevsky et al.
patent: 6487534 (2002-11-01), Thelen et al.
patent: 6526379 (2003-02-01), Rigazio et al.
patent: 6725195 (2004-04-01), Sankar et al.
patent: 6999925 (2006-02-01), Fischer et al.
patent: 7191130 (2007-03-01), Leggetter et al.
patent: 7209880 (2007-04-01), Gajic et al.
patent: 7451081 (2008-11-01), Gajic et al.
patent: 7480617 (2009-01-01), Chu et al.
patent: 7487091 (2009-02-01), Miyazaki
patent: 2002/0077823 (2002-06-01), Fox et al.
patent: 2003/0171931 (2003-09-01), Chang
patent: 4-125599 (1992-04-01), None
patent: 7-69711 (1995-07-01), None
patent: 9-81178 (1997-03-01), None
patent: 10-268893 (1998-10-01), None
patent: 11-143486 (1999-05-01), None
patent: 3251005 (2001-11-01), None
patent: 2002-236494 (2002-08-01), None
M. J. F. Gales, “Cluster Adaptive Training for Speech Recognition”, 1998, Proceedings of ICSLP98, pp. 1783-1786.
Shinichi Yoshizawa et al., “Model-Integration Training Based on Maximum Likeihood for Speech Recognition”, disclosed in a collective treatise of Acoustical Society of Japan, Sep. 17, 2003, pp. 105-106.
Yoshizawa et al., “Unsupervised Speaker Adaptation Based on Sufficient HMM Statistics of Selected Speakers”, Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '01), May 7, 2001, vol. 1, pp. 341-344.
Hihiri Imai, “Speech Recognition(Onsei Ninshiki)”, Kyoritsu Shuppan Kabushikigaisha, Nov. 25, 1995 pp. 150-152.
“Speech Information Processing(Onsei Jouhou Shori)”, Morikita Shuppan Kabushikigaisha, Jun. 30, 1988, pp. 100-104.
Kazuo Shigemasu, “Introduction to Bayesian Statistic(Beizu Toukei Nyumon)”, Tokyo Daigaku Shuppankai, Apr. 30, 1995, pp. 42-53.
Shinichi Yoshizawa et al., “Unsupervised Method for Learning Phonological Model Using Sufficient Statistic and Speaker Distance(Jubuntoukeiryo To Washakyori Wo Mochiita Onin Moderu No Kyoushi Nashi Gakushuhou”, the Institute of Electronics, Information and Communication Engineers, Mar. 1, 2002, vol. J85-D-II, No. 3, pp. 382-389.

Affiliated with

Also associated with

Rating

Standard-model generation for speech recognition using a... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Standard-model generation for speech recognition using a..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Standard-model generation for speech recognition using a... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4066309