Method and apparatus for speech recognition which is robust...

Details Method and apparatus for speech recognition which is robust... Method and apparatus for speech recognition which is robust...

2006-01-31

2006-01-31

McFadden, Susan (Department: 2655)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

Reexamination Certificate

active

06993483

ABSTRACT:
A speech recognizer suitable for distributed speech recognition is robust to missing speech feature vectors. Speech is transmitted via a packet switched network in the form of basic feature vectors. Missing feature vectors are detected and replacement feature vectors are estimated by interpolation of received data prior to speech recognition. Features may be converted and interpolation may be accomplished in a spectral domain.

REFERENCES:
patent: 4907277 (1990-03-01), Callens et al.
patent: 5710781 (1998-01-01), Zinser et al.
patent: 6006173 (1999-12-01), Wiese et al.
patent: 6351727 (2002-02-01), Wiese et al.
patent: 6775652 (2004-08-01), Cox et al.
patent: 0 872 827 (1998-10-01), None
patent: WO 95/17746 (1995-06-01), None
patent: WO 00/30072 (2000-05-01), None
Perkins et al IEEE Network, vol. 12, No. 5, Sep. 1998-Oct. 1998 pp. 40-48 XP002133605 A Survey of packet loss recovery techniques for streaming audio, no day.
Milner et al IEEE International Conference on Acoustics, Speech and Signal Processing Jun. 2000, pp 1791-1794 vol. 3, XP002156639 Robust speech recognition over IP networks, no day.

Affiliated with

Also associated with

Rating

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3573772