Hybrid model decomposition of speech and noise in a radial basis function neural model framework

Helge Bjarup Dissing Sørensen; Uwe Hartmann

doi:10.1109/ICASSP.1994.389570

Hybrid model decomposition of speech and noise in a radial basis function neural model framework

Helge Bjarup Dissing Sørensen
, Uwe Hartmann

Aalborg University

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

555 Downloads (Orbit)

Abstract

The aim of the paper is to focus on a new approach to automatic speech recognition in noisy environments where the noise has either stationary or non-stationary statistical characteristics. The aim is to perform automatic recognition of speech in the presence of additive car noise. The technique applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model

Original language	English
Title of host publication	Proceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing
Volume	Volume 2
Publisher	IEEE
Publication date	1994
Pages	657-660
ISBN (Print)	07-80-31775-0
DOIs	https://doi.org/10.1109/ICASSP.1994.389570
Publication status	Published - 1994
Event	1994 IEEE International Conference on Acoustics, Speech, and Signal Processing - Adelaide, Australia Duration: 19 Apr 1994 → 22 Apr 1994 Conference number: 19 http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3104

Conference

Conference	1994 IEEE International Conference on Acoustics, Speech, and Signal Processing
Number	19
Country/Territory	Australia
City	Adelaide
Period	19/04/1994 → 22/04/1994
Internet address	http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3104

Bibliographical note

Copyright: 1994 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Access to Document

10.1109/ICASSP.1994.389570

UweFinal published version, 326 KB

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{77db271aa9aa4235af27828514be153d,

title = "Hybrid model decomposition of speech and noise in a radial basis function neural model framework",

abstract = "The aim of the paper is to focus on a new approach to automatic speech recognition in noisy environments where the noise has either stationary or non-stationary statistical characteristics. The aim is to perform automatic recognition of speech in the presence of additive car noise. The technique applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model",

author = "S{\o}rensen, \{Helge Bjarup Dissing\} and Uwe Hartmann",

note = "Copyright: 1994 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE; 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '94 ; Conference date: 19-04-1994 Through 22-04-1994",

year = "1994",

doi = "10.1109/ICASSP.1994.389570",

language = "English",

isbn = "07-80-31775-0",

volume = "Volume 2",

pages = "657--660",

booktitle = "Proceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing",

publisher = "IEEE",

address = "United States",

url = "http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3104",

}

Sørensen, HBD & Hartmann, U 1994, Hybrid model decomposition of speech and noise in a radial basis function neural model framework. in Proceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing. vol. Volume 2, IEEE, pp. 657-660, 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing, Adelaide, South Australia, Australia, 19/04/1994. https://doi.org/10.1109/ICASSP.1994.389570

Hybrid model decomposition of speech and noise in a radial basis function neural model framework. / Sørensen, Helge Bjarup Dissing; Hartmann, Uwe.
Proceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing. Vol. Volume 2 IEEE, 1994. p. 657-660.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Hybrid model decomposition of speech and noise in a radial basis function neural model framework

AU - Sørensen, Helge Bjarup Dissing

AU - Hartmann, Uwe

N1 - Conference code: 19

PY - 1994

Y1 - 1994

N2 - The aim of the paper is to focus on a new approach to automatic speech recognition in noisy environments where the noise has either stationary or non-stationary statistical characteristics. The aim is to perform automatic recognition of speech in the presence of additive car noise. The technique applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model

AB - The aim of the paper is to focus on a new approach to automatic speech recognition in noisy environments where the noise has either stationary or non-stationary statistical characteristics. The aim is to perform automatic recognition of speech in the presence of additive car noise. The technique applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model

U2 - 10.1109/ICASSP.1994.389570

DO - 10.1109/ICASSP.1994.389570

M3 - Article in proceedings

SN - 07-80-31775-0

VL - Volume 2

SP - 657

EP - 660

BT - Proceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing

PB - IEEE

T2 - 1994 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 19 April 1994 through 22 April 1994

ER -

Hybrid model decomposition of speech and noise in a radial basis function neural model framework

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this