Binary Mask Estimation for Improved Speech Intelligibility in Reverberant Environments

被引:0
|
作者
Hazrati, Oldooz [1 ]
Lee, Jaewook [1 ]
Loizou, Philipos [1 ]
机构
[1] Univ Texas Dallas, CRSS, Richardson, TX 75080 USA
关键词
Binary mask; cochlear implant (CI); dereverberation; NOISE; RECOGNITION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A blind (non-ideal) time-frequency (T-F) masking technique is proposed for suppressing reverberation. A binary mask is estimated at each T-F unit by extracting a single variance-based feature from the reverberant signal and comparing its value against an adaptive threshold. The performance of the estimated binary mask is evaluated using intelligibility listening tests with hearing impaired listeners in four moderate to highly reverberant conditions. Results indicated that the proposed T-F masking technique yielded significant improvements in intelligibility even in highly reverberant conditions (T-60 = 1.0 s). This improvement was attributed to the recovery of the vowel/consonant boundaries which are severely smeared in reverberation.
引用
收藏
页码:162 / 165
页数:4
相关论文
共 50 条
  • [31] Using Acoustic Parameters for Intelligibility Prediction of Reverberant Speech
    Alghamdi, Ahmed
    Chan, Wai-Yip
    Fogerty, Daniel
    2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2018, : 2534 - 2538
  • [32] A CEPSTRUM PREFILTERING APPROACH FOR DOA ESTIMATION OF SPEECH SIGNAL IN REVERBERANT ENVIRONMENTS
    Nagase, Ryudo
    Oishi, Kunio
    Furukawa, Toshihiro
    2013 PROCEEDINGS OF THE 21ST EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2013,
  • [33] De-reverberation using DNN for Non-Reference Reverberant Speech Intelligibility Estimation
    Nakazawa, Kazushi
    Kondo, Kazuhiro
    2018 IEEE 7TH GLOBAL CONFERENCE ON CONSUMER ELECTRONICS (GCCE 2018), 2018, : 349 - 350
  • [34] Decreasing speaking-rate with steady-state suppression to improve speech intelligibility in reverberant environments
    Arai, Takayuki
    Nakata, Yuki
    Hodoshima, Nao
    Kurisu, Kiyohiro
    ACOUSTICAL SCIENCE AND TECHNOLOGY, 2007, 28 (04) : 282 - 285
  • [35] Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environment
    Keronen, Sami
    Kallasjoki, Heikki
    Remes, Ulpu
    Brown, Guy J.
    Gemmeke, Jort F.
    Palomaki, Kalle J.
    COMPUTER SPEECH AND LANGUAGE, 2013, 27 (03): : 798 - 819
  • [36] A NEW MASK-BASED OBJECTIVE MEASURE FOR PREDICTING THE INTELLIGIBILITY OF BINARY MASKED SPEECH
    Yu, Chengzhu
    Wojcicki, Kamil K.
    Loizou, P. C.
    Hansen, John H. L.
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7030 - 7033
  • [37] Improving Speech Intelligibility in Noise Using a Binary Mask That Is Based on Magnitude Spectrum Constraints
    Kim, Gibak
    Loizou, Philipos C.
    IEEE SIGNAL PROCESSING LETTERS, 2010, 17 (12) : 1010 - 1013
  • [38] Improving intelligibility of speech spoken under reverberant environment conditions: Effect of reverberation frequency characteristics on speech intelligibility
    Kambayashi, Chihiro
    Hodoshima, Nao
    ACOUSTICAL SCIENCE AND TECHNOLOGY, 2020, 41 (01) : 418 - 419
  • [39] Perceptual Characteristics of Chinese Speech Intelligibility in Simulated Reverberant Conditions
    Song, Hui
    Zhang, Siyu
    PROCEEDINGS OF 2020 IEEE 5TH INFORMATION TECHNOLOGY AND MECHATRONICS ENGINEERING CONFERENCE (ITOEC 2020), 2020, : 131 - 134
  • [40] IMPROVEMENTS TO NON-INTRUSIVE INTELLIGIBILITY PREDICTION FOR REVERBERANT SPEECH
    Nakazawa, Kazushi
    Kazuhiro, Kondo
    2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 608 - 613