Esophageal speech injection noise detection and rejection

Details Esophageal speech injection noise detection and rejection Esophageal speech injection noise detection and rejection

1997-04-16

1999-08-31

Hudspeth, David R.

Data processing: speech signal processing, linguistics, language

Speech signal processing

For storage or transmission

704270, 704255, 704233, 704208, G10L 302

Patent

active

059466499

ABSTRACT:
The present invention eliminates injection noise in speech produced by esophageal speakers. A speech input signal is digitized. One copy of the digitized signal is used for analysis and the other is passed through a gain switch to an amplifier as output. A Fast Fourier Transform and a mean value of the digitized speech input signal is calculated. The Fast Fourier Transform (FFT) is passed through a morphological filter to produce a filtered spectrum. An occurrence of injection noise is detected by calculating a derivative of the filtered spectrum and determining from the mean value and the derivative a location and value of a largest peak and a second largest peak in the filtered spectrum. If the largest peak is lower in frequency than the second largest peak, and if all points above 2 KHz are less than the mean, then an occurrence of injection noise has been detected. An occurrence of silence is detected by center-clipping the filtered spectrum and determining whether there is any energy within a sliding 10 millisecond window for a predetermined amount of time. If no energy is detected within a sliding 10 millisecond window for a predetermined amount time, then an occurrence of silence has been detected. The output speech signal is passed after the occurrence of injection noise has been detected; and is blocked following an occurrence of silence.

REFERENCES:
patent: 4308861 (1982-01-01), Kelly
patent: 4489440 (1984-12-01), Chaoui
patent: 4589136 (1986-05-01), Poldy et al.
patent: 4627095 (1986-12-01), Thompson
patent: 4718099 (1988-01-01), Hotvet
patent: 4736432 (1988-04-01), Cantrell
patent: 4837832 (1989-06-01), Fanshel
patent: 4862506 (1989-08-01), Landgarten et al.
patent: 4896358 (1990-01-01), Bahler et al.
patent: 5097509 (1992-03-01), Lennig
patent: 5157653 (1992-10-01), Genter
patent: 5319703 (1994-06-01), Drory
patent: 5326349 (1994-07-01), Baraff
patent: 5359663 (1994-10-01), Katz
patent: 5511009 (1996-04-01), Pastor
patent: 5621850 (1997-04-01), Kane et al.
patent: 5630015 (1997-05-01), Kane et al.
patent: 5710862 (1998-01-01), Urbanski
Article by Bernd Weinberg and James F. Bosma entitled "Similarities Between Glossopharyngeal Breathing and Injection Methods of Air Intake for Esophageal Speech" in the Journal of Speech and Hearing Disorders, vol. XXXI, No. 1, 1970.
Article by Leonard E. Baum entitled "An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of Markov Processes" published by Institute for Defense Analyses, Princeton, NJ, 1972.
Article by G. David Forney, Jr., entitled "The Viterbi Algorithm" published in the Proceedings of the IEEE, vol. 61, No. 3, Mar. 1973.
Article by Frederick Jelinek entitled "Continuous Speech Recognition by Statistical Methods" published in the Proceedings of the IEEE, vol. 64, vol. 4, Apr. 1976.
Article by Steven B. Davis and Paul Mermelstein entitled "Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences" published in IEEE Transactions on Acoustics, Speech and Signal Processing, vol. ASSP-28, No. 4, Aug. 1980.
Article by Joanne Robbins, Hilda B. Fisher, Eric C. Blom and Mark I. Singer entitled "A Comparative Acoustic Study of Normal Esophageal, and Tracheoesophageal Speech Production" published in the Journal of Speech and Hearing Disorders, vol. 49, 202-210, May 1984.
Article by Yingyong Qi entitled "Replacing Tracheoesophageal Voicing Sources Using LPC Synthesis" published in the Journal of Acoustical Society of America 88:1228-1235, 1990.
I. Pitas and A. N. Venetsanopoulos publication of "Nonlinear Digital Filters" by Kluwer Academic Publishers, Jun. 5, 1990.
Hong C. Leung, Benjamin Chigier and James R. Glass article entitled "A Comparative Study of Signal Representations and Classification Techniques for Speech Recognition" Proc. I CASSP-93, pp. II-680 to II-683, 1993.
John H. L. Hansen article entitled "Morphological Constrained Feature Enhancement with Adaptive Cepstral Compensation (MCE-ACC) or Speech Recognition in Noise and Lombard Effect" published in IEEE Transactions On Speech And Audio Processing, vol. 2, No. 4, Oct. 1994.
Article by Yingyong Qi, Bernd Weinberg and Ning Bi entitled "Enhancement of Female Esophageal and Tracheoesophageal Speech" published in the Journal of Acoustical Society of America, 98(5), P. 1, Nov. 1995.

Affiliated with

Also associated with

Rating

Esophageal speech injection noise detection and rejection does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Esophageal speech injection noise detection and rejection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Esophageal speech injection noise detection and rejection will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2428807