Method and apparatus for producing acoustic model

Details Method and apparatus for producing acoustic model Method and apparatus for producing acoustic model

2005-01-11

2005-01-11

Azad, Abul K. (Department: 2654)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S243000, C704S233000

Reexamination Certificate

active

06842734

ABSTRACT:
In an acoustic model producing apparatus, a plurality of noise samples are categorized into clusters so that a number of the clusters is smaller than that of noise samples. A noise sample is selected in each of the clusters to set the selected noise samples to second noise samples for training. On the other hand, untrained acoustic models are stored on a storage unit so that the untrained acoustic models are trained by using the second noise samples for training, thereby producing trained acoustic models for speech recognition so as to produce a trained acoustic model for speech recognition.

REFERENCES:
patent: 4590605 (1986-05-01), Hataoka et al.
patent: 5806029 (1998-09-01), Buhrke et al.
patent: 6782361 (2004-08-01), El-Maleh et al.
patent: 1199488 (1998-11-01), None
patent: 43 25 404 (1995-02-01), None
patent: 10-232694 (1998-09-01), None
patent: WO 9940571 (1999-08-01), None
Schultz et al.; Acoustic and Language Modeling of Human and Nonhuman Noise for Human-to-human Spontaneous Speech Recognition; IEEE 1995, pp. 293-296.*
“Evaluation of the Phoneme Recognition System for Noise mixed Data” by M. Hoshimi et al.; The Lecture Journal of the Acoustical Society of Japan; Mar., 1988; pp., 263-264 (w/Partial English translation).
Lee, “On Stochastic Feature and Model Compensation Approaches to Robust Speech Recognition”, Speech Communication, 1998, vol. 25, pps. 29-47.
Moreno et al., “Data-driven Environmental Compensation for Speech Recognition: A Unified Approach”, Speech Communication, 1998, vol. 24, pps. 267-285.

Affiliated with

Also associated with

Rating

Method and apparatus for producing acoustic 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 Method and apparatus for producing acoustic model, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for producing acoustic model will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3372545