Speech recognition with language-dependent model vectors

Details Speech recognition with language-dependent model vectors Speech recognition with language-dependent model vectors

2004-05-04

2009-12-08

Lerner, Martin (Department: 2626)

Data processing: speech signal processing, linguistics, language

Linguistics

Multilingual or national language support

C704S243000, C704S255000

Reexamination Certificate

active

07630878

ABSTRACT:
Speaker-dependent speech recognition is performed upon detecting a speech signal encompassing a voice command. The speech signal is divided into time frames and characterized in each detected time frame by forming a corresponding property vector. A language-independent feature vector sequence is formed from one or several property vectors and then stored. The language-independent feature vector sequence is allocated to a language-dependent sequence of model vectors in a speech resource having a plurality of model vectors. A piece of allocation information indicating allocation of the language-independent feature vector sequence to a language-dependent sequence of model vectors is stored, then the voice command allocated to the model vector sequence is identified.

REFERENCES:
patent: 5412716 (1995-05-01), Blaha
patent: 5623609 (1997-04-01), Kaye et al.
patent: 6006221 (1999-12-01), Liddy et al.
patent: 6085160 (2000-07-01), D'hoore et al.
patent: 6212500 (2001-04-01), Kohler
patent: 6253181 (2001-06-01), Junqua
patent: 6389393 (2002-05-01), Gong
patent: 6460017 (2002-10-01), Bub et al.
patent: RE38101 (2003-04-01), Vysotsky et al.
patent: 6658385 (2003-12-01), Gong et al.
patent: 6912499 (2005-06-01), Sabourin et al.
patent: 7043431 (2006-05-01), Riis et al.
patent: 7065487 (2006-06-01), Miyazawa
patent: 7072834 (2006-07-01), Zhou
patent: 7149688 (2006-12-01), Schalkwyk
patent: 7165027 (2007-01-01), Kellner et al.
patent: 7496498 (2009-02-01), Chu et al.
patent: 2002/0040296 (2002-04-01), Kienappel
patent: 2004/0078191 (2004-04-01), Tian et al.
patent: 2004/0088163 (2004-05-01), Schalkwyk
patent: 2005/0021335 (2005-01-01), Chaudhari et al.
patent: 41 08 785 (1991-10-01), None
patent: 195 33 541 (1997-03-01), None
patent: 196 24 988 (1998-01-01), None
patent: 196 35 754 (1998-03-01), None
patent: 0 797 185 (1997-09-01), None
patent: 1 220 196 (2002-07-01), None
patent: 2 242 148 (1991-09-01), None
patent: 02/05263 (2002-01-01), None
patent: 02/21513 (2002-03-01), None
D. L. Vos et al.; “Algorithm and DSP-Implementation for a Speaker-Independent Single-Word Speech Recognizer with Additional Speaker-Dependent Say-In Facility”; Proceedings IEEE Workshop on Interactive Voice Technology for Telecom Applications, Sep. 1996; pp. 53-56.
German Search Report for Application No. 103 34 400.4, dated Mar. 19, 2004.
International Search Report for European Application No. PCT/EP2004/050687; mailed Oct. 14, 2004.

Affiliated with

Also associated with

Rating

Speech recognition with language-dependent model vectors does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech recognition with language-dependent model vectors, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition with language-dependent model vectors will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4100092