Speech recognition using recursive time-domain high-pass filteri

Details Speech recognition using recursive time-domain high-pass filteri Speech recognition using recursive time-domain high-pass filteri

1997-05-27

1999-03-02

Hudspeth, David R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

704231, 704244, 704251, G10L 708

Patent

active

058783920

ABSTRACT:
A circuit arrangement for speech recognition carries out an analysis of a speech signal, extracting characteristic features. The extracted features are represented by spectral feature vectors which are compared with reference feature vectors stored for the speech signal to be recognized. The reference feature vectors are determined during a training phase in which a speech signal is recorded several times. A recognition result essentially depends on a quality of the spectral feature vectors and reference feature vectors. A recognition result essentially depends on a quality of the spectral feature vectors and reference feature vectors. A recursive high-pass filtering is performed in the time domain on the spectral feature vectors. Influences of noise signals on the recognition result are reduced by this and a high degree of speaker independence of the recognition is achieved. As a result, the circuit arrangement for speech recognition may also be used in systems requiring a speaker-independent speech recognition.

REFERENCES:
patent: 4038495 (1977-07-01), White
patent: 4736429 (1988-04-01), Niyada et al.
patent: 4809332 (1989-02-01), Jongman et al.
patent: 4827519 (1989-05-01), Fujimoto et al.
patent: 4833717 (1989-05-01), Nakamura et al.
patent: 4897878 (1990-01-01), Boll et al.
patent: 4941178 (1990-07-01), Chung
patent: 5054072 (1991-10-01), McAuley et al.
patent: 5056150 (1991-10-01), Yu et al.
patent: 5133012 (1992-07-01), Nitta
"Das Ohr als Nachrichtenempfanger", by Prof. Dr. Eberhard Zwicker et al, S. Hirzel Verlag, Stuttgart, 1967.
Sickert, et al., "Automische Spracheingabe und Sprachowsgabe", Verlag Markt und Technik, 1983.
"Sprachverarbeitung und Sprachubertragung" by K. Fellbaum, Berlin, Springer Verlag, 1984, p. 204.
"Speaker-Dependent Connected Speech Recognition via Dynamic Programming and Statistical Methods", by Bourlard et al, pp. 117-147, Bibliotheca Phonetics, No. 12, 1985.
"The Use of One-Stage Dynamic Programming Algorithm for Connected Word Recognition",by H. Ney, IEEE Trans. on Acoustics, Speech, and Signal Proc., vol. ASSP-30, No. 2, Apr. 1984, pp. 263-271.
Verfahren fur Friesprechen, Spracherkennung und Sprachcodierung in der SPS51, by W. Armbruster et al, Philips, pp. 35-41, PKI Teck. Mitt, Jan. 1990.
Hanson et al. "Subband or Cepstral Domain Filtering for Recognition of Lombard and Channel-Distorted Speech," ICASSP '93: Acoustics Speech & Signal Processing Conference, Apr. 1993.
Hynek Hermansky and Nelson Morgan, "RASTA Processing of Speech", IEEE Transactions on Speech and Audio Processing, vol. 2, No. 4, pp. 578-589, Oct. 1994.

Affiliated with

Also associated with

Rating

Speech recognition using recursive time-domain high-pass filteri 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 using recursive time-domain high-pass filteri, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition using recursive time-domain high-pass filteri will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-433274