Modulation Spectral Features for Intrusive Measurement of Reverberant Speech Quality

被引:0
|
作者
Ma, Sai [1 ]
Zhang, Hui [1 ]
Xie, Lingyun [1 ]
Xie, Xi [1 ]
机构
[1] Commun Univ China, Beijing, Peoples R China
来源
关键词
Reverberation; Direct-to-Reverberant energy ratio; Modulation; Instantaneous Frequency; Mutual Information; INTELLIGIBILITY;
D O I
10.1007/978-981-13-8138-6_24
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Temporal fine structure includes temporal envelope and fine structure which also called carrier, and instantaneous frequency is the partial derivative of the carrier. An intrusive reverberant speech quality measurement is investigated with the representation of corresponding instantaneous frequency. A Gammatone filterbank is used to simulate auditory mechanism and a modulation filterbank is used to improve frequency resolution. The mean mutual information between reference and reverberant modulation spectral instantaneous frequency probability distribution is taken as the final measurement score. Experimental results show the proposed method outperforming two benchmark algorithms in some practical application conditions.
引用
收藏
页码:284 / 295
页数:12
相关论文
共 50 条
  • [21] Non-intrusive Objective Speech Quality Measurement based on GMM and SVR for Narrowband and Wideband Speech
    Wang, Jing
    Luo, Juan
    Zhao, Shenghui
    Kuang, Jingming
    2008 11TH IEEE SINGAPORE INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS (ICCS), VOLS 1-3, 2008, : 193 - 198
  • [22] Non-intrusive objective speech quality measurement based on fuzzy GMM and SVR for narrowband speech
    Wang, Jing
    Zhang, Ying
    Zhao, Sheng-Hui
    Kuang, Jing-Ming
    Journal of Beijing Institute of Technology (English Edition), 2010, 19 (01): : 76 - 81
  • [23] Non-Intrusive Objective Speech Quality Measurement Based on Fuzzy GMM and SVR for Narrowband Speech
    王晶
    张莹
    赵胜辉
    匡镜明
    Journal of Beijing Institute of Technology, 2010, 19 (01) : 76 - 81
  • [24] Non-intrusive speech quality assessment using several combinations of auditory features
    Dubey, Rajesh
    Kumar, Arun
    INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2013, 16 (01) : 89 - 101
  • [25] Strategies for improving audible quality and speech recognition accuracy of reverberant speech
    Gillespie, BW
    Atlas, LE
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING I, 2003, : 676 - 679
  • [26] Intrusive Quality Measurement of Noisy and Enhanced Speech based on i-Vector Similarity
    Avila, Anderson R.
    Alam, Jahangir
    O'Shaughnessy, Douglas
    Falk, Tiago H.
    2019 ELEVENTH INTERNATIONAL CONFERENCE ON QUALITY OF MULTIMEDIA EXPERIENCE (QOMEX), 2019,
  • [27] A Novel Non-intrusive Objective Speech Quality Measurement based on GMM and SVR
    Wang, Jing
    Luo, Juan
    Zhao, Shenghui
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 691 - 694
  • [28] EVALUATION OF OBJECTIVE MEASURES FOR QUALITY ASSESSMENT OF REVERBERANT SPEECH
    Kokkinakis, Kostas
    Loizou, Philipos C.
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 2420 - 2423
  • [29] Fusion of bottleneck, spectral and modulation spectral features for improved speaker verification of neutral and whispered speech
    Sarria-Paja, Milton
    Falk, Tiago H.
    SPEECH COMMUNICATION, 2018, 102 : 78 - 86
  • [30] Non-Intrusive Speech Quality Prediction Using Modulation Energies and LSTM-Network
    Cauchi, Benjamin
    Siedenburg, Kai
    Santos, Joao E.
    Falk, Tiago H.
    Doclo, Simon
    Goetze, Stefan
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2019, 27 (07) : 1151 - 1163