Comparative Evaluation of Single-Channel MMSE-Based Noise Reduction Schemes for Speech Recognition

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...

Full description

Bibliographic Details
Main Authors: Emanuele Principi, Simone Cifani, Rudy Rotili, Stefano Squartini, Francesco Piazza
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

Similar Items