Linearized distortion model for robust speech recognition in noisy environments

被引：0
|
作者：
He, Yong-Jun [1 ,2 ]
Han, Ji-Qing [1 ]
机构：
[1] School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China
[2] School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China
来源：
Tongxin Xuebao/Journal on Communications | 2010年 / 31卷 / 09期
关键词：
Linearization - Piecewise linear techniques;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The robustness of speech recognition system in noisy environments was investigated. The distortion model in Mel-frequency cepstral coefficient (MFCC) domain is highly non-linear and difficult to deal with. A new linear distortion model was proposed by replacing the logarithm operation with its piecewise linear interpolation function. Then the estimation of noise parameters and compensation of acoustic models were provided. The proposed method can avoid model error introduced by utilizing linearization methods based on vector Taylor series (VTS) expansion, and significantly improve the robustness of recognizer in noisy environments.
引用
收藏
页码：8 / 14
相关论文
共 50 条
  • [21] Robust recognition of noisy speech using speech enhancement
    Xu, YF
    Zhang, JJ
    Yao, KS
    Cao, ZG
    Ma, ZX
    2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 734 - 737
  • [22] Multisensory benefits for speech recognition in noisy environments
    Oh, Yonghee
    Schwalm, Meg
    Kalpin, Nicole
    FRONTIERS IN NEUROSCIENCE, 2022, 16
  • [23] Speech Emotion Recognition in Noisy and Reverberant Environments
    Heracleous, Panikos
    Yasuda, Keiji
    Sugaya, Fumiaki
    Yoneyama, Akio
    Hashimoto, Masayuki
    2017 SEVENTH INTERNATIONAL CONFERENCE ON AFFECTIVE COMPUTING AND INTELLIGENT INTERACTION (ACII), 2017, : 262 - 266
  • [24] Speech Recognition On Mobile Devices In Noisy Environments
    Yurtcan, Yaser
    Kilic, Banu Gunel
    2018 26TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2018,
  • [25] NOT ALL FEATURES ARE EQUAL: SELECTION OF ROBUST FEATURES FOR SPEECH EMOTION RECOGNITION IN NOISY ENVIRONMENTS
    Leem, Seong-Gyun
    Fulford, Daniel
    Onnela, Jukka-Pekka
    Gard, David
    Busso, Carlos
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 6447 - 6451
  • [26] Robust Recognition of English Speech in Noisy Environments Using Frequency Warped Signal Processing
    Upadhyay, Navneet
    Gamboa Rosales, Hamurabi
    NATIONAL ACADEMY SCIENCE LETTERS-INDIA, 2018, 41 (01): : 15 - 22
  • [27] Robust Recognition of English Speech in Noisy Environments Using Frequency Warped Signal Processing
    Navneet Upadhyay
    Hamurabi Gamboa Rosales
    National Academy Science Letters, 2018, 41 : 15 - 22
  • [28] AMPLITUDE MODULATION SPECTROGRAM BASED FEATURES FOR ROBUST SPEECH RECOGNITION IN NOISY AND REVERBERANT ENVIRONMENTS
    Moritz, Niko
    Anemueller, Joern
    Kollmeier, Birger
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5492 - 5495
  • [29] Compensation of speech enhancement distortion for robust speech recognition
    Ding, P
    Cao, ZG
    2002 IEEE REGION 10 CONFERENCE ON COMPUTERS, COMMUNICATIONS, CONTROL AND POWER ENGINEERING, VOLS I-III, PROCEEDINGS, 2002, : 449 - 452
  • [30] Robust speech recognition in car environments
    Shozakai, M
    Nakamura, S
    Shikano, K
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 269 - 272
12345