NOISE REDUCTION FOR SPEECH ENHANCEMENT IN CARS: NON-LINEAR SPECTRAL SUBTRACTION / KALMAN FILTERING

P. Lockwood; C. Baillargeat; J. M. Gillot; J. Boudy; G. Faucon

NOISE REDUCTION FOR SPEECH ENHANCEMENT IN CARS: NON-LINEAR SPECTRAL SUBTRACTION / KALMAN FILTERING

P. Lockwood, C. Baillargeat, J. M. Gillot, J. Boudy, G. Faucon

Research output: Contribution to conference › Paper › peer-review

Abstract

Achieving a good quality of speech transmission and reliable performance in speech recognition in the car is an important challenge especially in the context of mobile telephony applications where the user can access the telephone functions by voice. The break through such a technology is appealing, since the driver can concentrate completely and safely on his task while composing and conversing in a full handfree mode. This paper compares approaches enhancing noisy speech with applications both for speech transmission and speech recognition, two approaches have been retained: a temporal approach based on Kalman filtering and a frequential approach based on spectral subtraction. These methods have been extended further yielding new algorithms for speech processing in noise. We report comparative experiments made with various implementations of the speech enhancers. These include a nonlinear spectral subtracter [12] and several implementations of a Kalman filter, including new noise whitening schemes.

Original language	English
Pages	83-86
Number of pages	4
Publication status	Published - 1 Jan 1991
Externally published	Yes
Event	2nd European Conference on Speech Communication and Technology, EUROSPEECH 1991 - Genova, Italy Duration: 24 Sept 1991 → 26 Sept 1991

Conference

Conference	2nd European Conference on Speech Communication and Technology, EUROSPEECH 1991
Country/Territory	Italy
City	Genova
Period	24/09/91 → 26/09/91

Cite this

@conference{ba4dc23dd7254fd68207e1e845c9136b,

title = "NOISE REDUCTION FOR SPEECH ENHANCEMENT IN CARS: NON-LINEAR SPECTRAL SUBTRACTION / KALMAN FILTERING",

abstract = "Achieving a good quality of speech transmission and reliable performance in speech recognition in the car is an important challenge especially in the context of mobile telephony applications where the user can access the telephone functions by voice. The break through such a technology is appealing, since the driver can concentrate completely and safely on his task while composing and conversing in a full handfree mode. This paper compares approaches enhancing noisy speech with applications both for speech transmission and speech recognition, two approaches have been retained: a temporal approach based on Kalman filtering and a frequential approach based on spectral subtraction. These methods have been extended further yielding new algorithms for speech processing in noise. We report comparative experiments made with various implementations of the speech enhancers. These include a nonlinear spectral subtracter [12] and several implementations of a Kalman filter, including new noise whitening schemes.",

author = "P. Lockwood and C. Baillargeat and Gillot, \{J. M.\} and J. Boudy and G. Faucon",

note = "Publisher Copyright: {\textcopyright} 2nd European Conference on Speech Communication and Technology, EUROSPEECH 1991.; 2nd European Conference on Speech Communication and Technology, EUROSPEECH 1991 ; Conference date: 24-09-1991 Through 26-09-1991",

year = "1991",

month = jan,

day = "1",

language = "English",

pages = "83--86",

}

TY - CONF

T1 - NOISE REDUCTION FOR SPEECH ENHANCEMENT IN CARS

T2 - 2nd European Conference on Speech Communication and Technology, EUROSPEECH 1991

AU - Lockwood, P.

AU - Baillargeat, C.

AU - Gillot, J. M.

AU - Boudy, J.

AU - Faucon, G.

PY - 1991/1/1

Y1 - 1991/1/1

N2 - Achieving a good quality of speech transmission and reliable performance in speech recognition in the car is an important challenge especially in the context of mobile telephony applications where the user can access the telephone functions by voice. The break through such a technology is appealing, since the driver can concentrate completely and safely on his task while composing and conversing in a full handfree mode. This paper compares approaches enhancing noisy speech with applications both for speech transmission and speech recognition, two approaches have been retained: a temporal approach based on Kalman filtering and a frequential approach based on spectral subtraction. These methods have been extended further yielding new algorithms for speech processing in noise. We report comparative experiments made with various implementations of the speech enhancers. These include a nonlinear spectral subtracter [12] and several implementations of a Kalman filter, including new noise whitening schemes.

AB - Achieving a good quality of speech transmission and reliable performance in speech recognition in the car is an important challenge especially in the context of mobile telephony applications where the user can access the telephone functions by voice. The break through such a technology is appealing, since the driver can concentrate completely and safely on his task while composing and conversing in a full handfree mode. This paper compares approaches enhancing noisy speech with applications both for speech transmission and speech recognition, two approaches have been retained: a temporal approach based on Kalman filtering and a frequential approach based on spectral subtraction. These methods have been extended further yielding new algorithms for speech processing in noise. We report comparative experiments made with various implementations of the speech enhancers. These include a nonlinear spectral subtracter [12] and several implementations of a Kalman filter, including new noise whitening schemes.

M3 - Paper

AN - SCOPUS:84875955630

SP - 83

EP - 86

Y2 - 24 September 1991 through 26 September 1991

ER -

NOISE REDUCTION FOR SPEECH ENHANCEMENT IN CARS: NON-LINEAR SPECTRAL SUBTRACTION / KALMAN FILTERING

Abstract

Conference

Fingerprint

Cite this