Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition
One of the big challenges in the field of Automatic Speech Recognition (ASR) consists in developing suitable solutions able to work properly also in adverse acoustic conditions, like in presence of additive noise and/or in reverberant rooms. Recently a certain attention has been paid to deeply integ...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2010-01-01
|
Series: | Journal of Electrical and Computer Engineering |
Online Access: | http://dx.doi.org/10.1155/2010/962103 |
id |
doaj-b8763091e15244a7b648aae16988f2c0 |
---|---|
record_format |
Article |
spelling |
doaj-b8763091e15244a7b648aae16988f2c02021-07-02T02:15:40ZengHindawi LimitedJournal of Electrical and Computer Engineering2090-01472090-01552010-01-01201010.1155/2010/962103962103Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech RecognitionEmanuele Principi0Simone Cifani1Rudy Rotili2Stefano Squartini3Francesco Piazza43MediaLabs, Department of Biomedical Engineering, Electronics and Telecommunications, Polytechnic University of Marche, 60121 Ancona, Italy3MediaLabs, Department of Biomedical Engineering, Electronics and Telecommunications, Polytechnic University of Marche, 60121 Ancona, Italy3MediaLabs, Department of Biomedical Engineering, Electronics and Telecommunications, Polytechnic University of Marche, 60121 Ancona, Italy3MediaLabs, Department of Biomedical Engineering, Electronics and Telecommunications, Polytechnic University of Marche, 60121 Ancona, Italy3MediaLabs, Department of Biomedical Engineering, Electronics and Telecommunications, Polytechnic University of Marche, 60121 Ancona, ItalyOne of the big challenges in the field of Automatic Speech Recognition (ASR) consists in developing suitable solutions able to work properly also in adverse acoustic conditions, like in presence of additive noise and/or in reverberant rooms. Recently a certain attention has been paid to deeply integrate the noise suppressor in the feature extraction pipeline. In this paper, different single-channel MMSE-based noise reduction schemes have been implemented both in the frequency and cepstral domains and the related recognition performances evaluated on the AURORA2 and AURORA4 databases, therefore providing a useful reference for the scientific community.http://dx.doi.org/10.1155/2010/962103 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Emanuele Principi Simone Cifani Rudy Rotili Stefano Squartini Francesco Piazza |
spellingShingle |
Emanuele Principi Simone Cifani Rudy Rotili Stefano Squartini Francesco Piazza Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition Journal of Electrical and Computer Engineering |
author_facet |
Emanuele Principi Simone Cifani Rudy Rotili Stefano Squartini Francesco Piazza |
author_sort |
Emanuele Principi |
title |
Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition |
title_short |
Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition |
title_full |
Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition |
title_fullStr |
Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition |
title_full_unstemmed |
Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition |
title_sort |
comparative evaluation of single-channel mmse-based noise reduction schemes for speech recognition |
publisher |
Hindawi Limited |
series |
Journal of Electrical and Computer Engineering |
issn |
2090-0147 2090-0155 |
publishDate |
2010-01-01 |
description |
One of the big challenges in the field of Automatic
Speech Recognition (ASR) consists in developing suitable solutions
able to work properly also in adverse acoustic conditions,
like in presence of additive noise and/or in reverberant rooms.
Recently a certain attention has been paid to deeply integrate the
noise suppressor in the feature extraction pipeline. In this paper,
different single-channel MMSE-based noise reduction schemes
have been implemented both in the frequency and cepstral
domains and the related recognition performances evaluated on
the AURORA2 and AURORA4 databases, therefore providing a
useful reference for the scientific community. |
url |
http://dx.doi.org/10.1155/2010/962103 |
work_keys_str_mv |
AT emanueleprincipi comparativeevaluationofsinglechannelmmsebasednoisereductionschemesforspeechrecognition AT simonecifani comparativeevaluationofsinglechannelmmsebasednoisereductionschemesforspeechrecognition AT rudyrotili comparativeevaluationofsinglechannelmmsebasednoisereductionschemesforspeechrecognition AT stefanosquartini comparativeevaluationofsinglechannelmmsebasednoisereductionschemesforspeechrecognition AT francescopiazza comparativeevaluationofsinglechannelmmsebasednoisereductionschemesforspeechrecognition |
_version_ |
1721343629832749056 |