Perceptual evaluation of blind source separation for robust speech recognition

被引：41
|
作者：
Di Persia, Leandro [1 ]
Milone, Diego [1 ]
Rufiner, Hugo Leonardo [1 ,2 ]
Yanagida, Masuzo [3 ]
机构：
[1] Univ Nacl Litoral, Grp Invest Senales & Inteligencia Computac, Fac Ingn & Ciencias Hidr, RA-3000 Santa Fe, Argentina
[2] Univ Nacl Entre Rios, Fac Ingn, Lab Cibernet, RA-3100 Parana, Argentina
[3] Doshisha Univ, Dept Intelligent Informat Engn & Sci, Kyotanabe 6100321, Japan
来源：
SIGNAL PROCESSING | 2008年 / 88卷 / 10期
关键词：
quality measures; blind source separation; robust speech recognition; reverberation; PESQ;
D O I：
10.1016/j.sigpro.2008.04.006
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In a previous article, an evaluation of several objective quality measures as predictors of recognition rate after the application of a blind source separation algorithm was reported. In this work, the experiments were repeated using some new measures, based on the perceptual evaluation of speech quality (PESQ), which is part of the ITU P862 standard for evaluation of communication systems. The raw PESQ and a nonlinearly transformed PESQ were evaluated, together with several composite measures. The results show that the PESQ-based measures outperformed all the measures reported in the previous work. Based on these results, we recommend the use of PESQ-based measures to evaluate blind source separation algorithms for automatic speech recognition. (C) 2008 Published by Elsevier B.V.
引用
收藏
页码：2578 / 2583
页数：6
相关论文
共 50 条
  • [1] A new perceptual convolutive blind source separation algorithm for speech separation
    Pan, QF
    Aboulnasr, T
    [J]. 2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3, 2004, : 323 - 326
  • [2] Objective quality evaluation in blind source separation for speech recognition in a real room
    Di Persia, Leandro
    Yanagida, Masuzo
    Rufiner, Hugo Leonardo
    Milone, Diego
    [J]. SIGNAL PROCESSING, 2007, 87 (08) : 1951 - 1965
  • [3] Blind speech separation of nonlinear convolutive mixtures for robust speech recognition
    Koutras, A.
    Dermatas, E.
    Kokkinakis, G.
    [J]. Control and Intelligent Systems, 2002, 30 (02) : 83 - 90
  • [4] New Robust Blind Source Separation Algorithm for Speech Enhancement
    Djendi, Mohamed
    Zoulikha, Meriem
    [J]. ADVANCED CONTROL ENGINEERING METHODS IN ELECTRICAL ENGINEERING SYSTEMS, 2019, 522 : 526 - 536
  • [5] Blind source extraction for robust speech recognition in multisource noisy environments
    Nesta, Francesco
    Matassoni, Marco
    [J]. COMPUTER SPEECH AND LANGUAGE, 2013, 27 (03): : 703 - 725
  • [6] Modeling perceptual similarity of audio signals for blind source separation evaluation
    Fox, Brendan
    Sabin, Andrew
    Pardo, Bryan
    Zopf, Alec
    [J]. INDEPENDENT COMPONENT ANALYSIS AND SIGNAL SEPARATION, PROCEEDINGS, 2007, 4666 : 454 - +
  • [7] Blind Audio Source Separation by NTF and its Perceptual Quality Evaluation
    Keyder, M. Altug
    Guensel, Bilge
    [J]. 2008 IEEE 16TH SIGNAL PROCESSING, COMMUNICATION AND APPLICATIONS CONFERENCE, VOLS 1 AND 2, 2008, : 627 - 630
  • [8] Experiments in audio source separation with one sensor for robust speech recognition
    Benaroya, Laurent
    Bimbot, Frederic
    Gravier, Guillaume
    Gribonval, Remi
    [J]. SPEECH COMMUNICATION, 2006, 48 (07) : 848 - 854
  • [9] A post-filter perceptual convolutive blind source separation approach for speech signal
    Pan, QF
    Aboulnasr, T
    [J]. 2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3, 2004, : 327 - 330
  • [10] Perceptual wavelet filtering for robust speech recognition
    Van Pham, Tuan
    Stark, Michael
    Kubin, Gernot
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4385 - 4388
12345