Data-driven filtering of cepstral time trajectories for...

Details Data-driven filtering of cepstral time trajectories for... Data-driven filtering of cepstral time trajectories for...

2006-04-25

2006-04-25

Storm, Donald L. (Department: 2654)

Data processing: speech signal processing, linguistics, language

Speech signal processing

For storage or transmission

C704S234000

Reexamination Certificate

active

07035797

ABSTRACT:
A method and apparatus for speech processing in a distributed speech recognition system having a front-end and a back-end. The speech processing steps in the front-end are as follows: extracting speech features from a speech signal and normalizing the speech features in order to alter the power of the noise component in the modulation spectrum in relation to the power of the signal component, especially with frequencies above 10 Hz. A low-pass filter is then used to filter the normalized modulation spectrum in order to improve the signal-to-noise ratio (SNR) in the speech signal. The combination of feature vector normalization and low-pass filtering is effective in noise removal, especially in a low SNR environment.

REFERENCES:
patent: 4227176 (1980-10-01), Moshier
patent: 6092039 (2000-07-01), Zingher
patent: 6157909 (2000-12-01), Mauuary et al.
patent: 6266633 (2001-07-01), Higgins et al.
patent: 6308155 (2001-10-01), Kingsbury et al.
patent: 2003/0004720 (2003-01-01), Garadadri et al.
patent: 0871157 (1998-10-01), None
Tom Claes and Dirk Van Compernolle, “SNR-Normalization for Robust Speech Recognition,” Proc. Int. Conf. Acoust., Speech, and Sig. Proc., vol. 1, pp. 331-334, 1996.
ETSI ES 201 108 v1.1.2 (Apr. 2000) Speech Processing, Transmission and Quality aspects (STQ); Distributed speech recognition; Front-end feature extraction algorithm; Compression algorithms, pp 1-20.
Nokia ETSI—STQ W1008; DSR Front-End Proposal for the Advanced Noise Robust Front-End; Oct. 29, 1999, 9 PAGES.
Data-Driven Design of RASTA-like Filters; van Vuuren et al.; Proc. EUROSPEECH, pp. 409-412, 1997.
“RASTA Processing of Speech”, Hermansky, IEEE Trans. on Speech and Audio Processing, vol. 2, No. 4, pp. 578-589, 1994.
“Cepstral domain segmental feature vector normalization for noise robust speech recognition”, O. Viikki et al., Speech Communication, vol. 25, pp. 133-147, 1998, Elsevier.

Affiliated with

Also associated with

Rating

Data-driven filtering of cepstral time trajectories for... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Data-driven filtering of cepstral time trajectories for..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Data-driven filtering of cepstral time trajectories for... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3612967