A new speech enhancement technique with application to speaker identification

Mzchad A. Ramalho; Richard J. Mammone

doi:10.1109/ICASSP.1994.389363

A new speech enhancement technique with application to speaker identification

Mzchad A. Ramalho, Richard J. Mammone

School of Engineering, Electrical & Computer Engineering

Research output: Contribution to journal › Conference article › peer-review

4 Scopus citations

Abstract

Speaker Identification (SI) and speech recognition systems display a strong sensitivity to ambient noise conditions [l]. It is known that the performance of these systems is maximized when tmined under conditions that approziinale the testing environment. However, these systems generally do not perform well when there is no noise or when the level or characteristics of the noise changes. A new speech enhancement technique is presented that, when used with a standard cepstrnm-based SI system, significantly reduces the sensitivity of the SI system to mismatches in the noise euvironnient between training and testing.

Original language	English (US)
Article number	389363
Pages (from-to)	I29-I32
Journal	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	1
DOIs	https://doi.org/10.1109/ICASSP.1994.389363
State	Published - 1994
Event	Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) - Adelaide, Aust Duration: Apr 19 1994 → Apr 22 1994

All Science Journal Classification (ASJC) codes

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.1994.389363

Cite this

@article{e1f701a95a4241df8a976bf4f95704f1,

title = "A new speech enhancement technique with application to speaker identification",

abstract = "Speaker Identification (SI) and speech recognition systems display a strong sensitivity to ambient noise conditions [l]. It is known that the performance of these systems is maximized when tmined under conditions that approziinale the testing environment. However, these systems generally do not perform well when there is no noise or when the level or characteristics of the noise changes. A new speech enhancement technique is presented that, when used with a standard cepstrnm-based SI system, significantly reduces the sensitivity of the SI system to mismatches in the noise euvironnient between training and testing.",

author = "Ramalho, {Mzchad A.} and Mammone, {Richard J.}",

note = "Publisher Copyright: {\textcopyright} 1994 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.; Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) ; Conference date: 19-04-1994 Through 22-04-1994",

year = "1994",

doi = "10.1109/ICASSP.1994.389363",

language = "English (US)",

volume = "1",

pages = "I29--I32",

journal = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

issn = "1520-6149",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - A new speech enhancement technique with application to speaker identification

AU - Ramalho, Mzchad A.

AU - Mammone, Richard J.

PY - 1994

Y1 - 1994

N2 - Speaker Identification (SI) and speech recognition systems display a strong sensitivity to ambient noise conditions [l]. It is known that the performance of these systems is maximized when tmined under conditions that approziinale the testing environment. However, these systems generally do not perform well when there is no noise or when the level or characteristics of the noise changes. A new speech enhancement technique is presented that, when used with a standard cepstrnm-based SI system, significantly reduces the sensitivity of the SI system to mismatches in the noise euvironnient between training and testing.

AB - Speaker Identification (SI) and speech recognition systems display a strong sensitivity to ambient noise conditions [l]. It is known that the performance of these systems is maximized when tmined under conditions that approziinale the testing environment. However, these systems generally do not perform well when there is no noise or when the level or characteristics of the noise changes. A new speech enhancement technique is presented that, when used with a standard cepstrnm-based SI system, significantly reduces the sensitivity of the SI system to mismatches in the noise euvironnient between training and testing.

UR - http://www.scopus.com/inward/record.url?scp=84945971309&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84945971309&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.1994.389363

DO - 10.1109/ICASSP.1994.389363

M3 - Conference article

AN - SCOPUS:84945971309

SN - 1520-6149

VL - 1

SP - I29-I32

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

M1 - 389363

T2 - Proceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6)

Y2 - 19 April 1994 through 22 April 1994

ER -

A new speech enhancement technique with application to speaker identification

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this