Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2011-08-02
2011-08-02
Wozniak, James S. (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S210000, C704S215000, C704S226000, C704S233000
Reexamination Certificate
active
07991614
ABSTRACT:
A speech recognition system includes the following: a feature calculating unit; a sound level calculating unit that calculates an input sound level in each frame; a decoding unit that matches the feature of each frame with an acoustic model and a linguistic model, and outputs a recognized word sequence; a start-point detector that determines a start frame of a speech section based on a reference value; an end-point detector that determines an end frame of the speech section based on a reference value; and a reference value updating unit that updates the reference value in accordance with variations in the input sound level. The start-point detector updates the start frame every time the reference value is updated. The decoding unit starts matching before being notified of the end frame and corrects the matching results every time it is notified of the start frame. The speech recognition system can suppress a delay in response time while performing speech recognition based on a proper speech section.
REFERENCES:
patent: 4984275 (1991-01-01), Watanabe et al.
patent: 5121428 (1992-06-01), Uchiyama et al.
patent: 5220609 (1993-06-01), Watanabe et al.
patent: 5740318 (1998-04-01), Naito et al.
patent: 5794195 (1998-08-01), Hormann et al.
patent: 6088670 (2000-07-01), Takada
patent: 6216103 (2001-04-01), Wu et al.
patent: 6236970 (2001-05-01), Imai et al.
patent: 6324509 (2001-11-01), Bi et al.
patent: 6405164 (2002-06-01), Pinai
patent: 6782363 (2004-08-01), Lee et al.
patent: 7277853 (2007-10-01), Bou-Ghazale et al.
patent: 7412376 (2008-08-01), Florencio et al.
patent: 2001/0010037 (2001-07-01), Imai et al.
patent: 2003/0061036 (2003-03-01), Garudadri et al.
patent: 2004/0064314 (2004-04-01), Aubert et al.
patent: 2004/0162727 (2004-08-01), Kiuchi et al.
patent: 2005/0055201 (2005-03-01), Florencio et al.
patent: 2005/0171771 (2005-08-01), Yasunaga et al.
patent: 2006/0136210 (2006-06-01), Menendez-Pidal et al.
patent: 2006/0241948 (2006-10-01), Abrash et al.
patent: 0 944 036 (1999-09-01), None
patent: 1 517 299 (2005-03-01), None
patent: 1 944 753 (2008-07-01), None
patent: 57-97599 (1982-06-01), None
patent: 60-499 (1985-01-01), None
patent: 62-293299 (1987-12-01), None
patent: B2 2625682 (1988-04-01), None
patent: A 2-236599 (1990-09-01), None
patent: A 7-92989 (1995-04-01), None
patent: B2 3160228 (1998-06-01), None
patent: A 10-301600 (1998-11-01), None
patent: A 2000-250568 (2000-09-01), None
patent: A 2002-258882 (2002-09-01), None
patent: A 2005-31632 (2005-02-01), None
Li et al. “Robust Endpoint Detection and Energy Normalization for Real-Time Speech and Speaker Recognition”, IEEE Transactions on Speech and Audio Processing, vol. 10, No. 3, Mar. 2002.
Harada Shouji
Washio Nobuyuki
Fujitsu Limited
Greer Burns & Crain Ltd.
He Jialong
Wozniak James S.
LandOfFree
Correction of matching results for 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 Correction of matching results for speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Correction of matching results for speech recognition will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2738696