Noise Robust Speech Features for Automatic Continuous Speech Recognition using Running Spectrum Analysis

被引：2
|
作者：
Ohnuki, Kazunaga [1 ]
Takahashi, Wataru [1 ]
Yoshizawa, Shingo [1 ]
Miyanaga, Yoshikazu [1 ]
机构：
[1] Hokkaido Univ, Grad Sch Informat Sci & Technol, Sapporo, Hokkaido 0600814, Japan
来源：
2008 INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES | 2008年
关键词：
D O I：
10.1109/ISCIT.2008.4700172
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this report, new robust speech feature is introduced and applied for an automatic continuous speech recognition system. Using these features, the noise robust continuous speech recognition can be realized. The new running spectrum analysis (RSA) method is used in order to remove un-speech components over 15 Hz in modulation spectrum domain. Using RSA, speech features are emphasized for the design of tri-phone HMM where the tri-phone HMM is used in continuous speech recognition. In order to show the performance of the developed system, some comparisons with conventional one are given in experiments.
引用
收藏
页码：150 / 153
页数：4
相关论文
共 50 条
  • [31] JOINT NOISE ADAPTIVE TRAINING FOR ROBUST AUTOMATIC SPEECH RECOGNITION
    Narayanan, Arun
    Wang, DeLiang
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [32] Noise Spectrum Estimation Using Line Spectral Frequencies for Robust Speech Recognition
    Jang, Gil-Jin
    Park, Jeong-Sik
    Kim, Sanghun
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2012, 31 (03): : 179 - 187
  • [33] Feature-based Noise Robust Speech Recognition on an Indonesian Language Automatic Speech Recognition System
    Satriawan, Cil Hardianto
    Lestari, Dessi Puji
    2014 International Conference on Electrical Engineering and Computer Science (ICEECS), 2014, : 42 - 46
  • [34] Robust Continuous On-device Personalization for Automatic Speech Recognition
    Sim, Khe Chai
    Chandorkar, Angad
    Gao, Fan
    Chua, Mason
    Munkhdalai, Tsendsuren
    Beaufays, Francoise
    INTERSPEECH 2021, 2021, : 1284 - 1288
  • [35] ROBUST EXCITATION-BASED FEATURES FOR AUTOMATIC SPEECH RECOGNITION
    Drugman, Thomas
    Stylianou, Yannis
    Chen, Langzhou
    Chen, Xie
    Gales, Mark J. F.
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 4664 - 4668
  • [36] Signal subspace method with continuous noise estimation and its efficiency in robust automatic speech recognition
    Jare, Bojan
    Babič, Rudolf
    Elektrotehniski Vestnik/Electrotechnical Review, 2007, 74 (04): : 229 - 235
  • [37] Signal subspace method with continuous noise estimation and its efficiency in robust automatic speech recognition
    Jarc, Bojan
    Babic, Rudolf
    ELEKTROTEHNISKI VESTNIK-ELECTROCHEMICAL REVIEW, 2007, 74 (04): : 229 - 235
  • [38] STRUCTURED DISCRIMINATIVE MODELS FOR NOISE ROBUST CONTINUOUS SPEECH RECOGNITION
    Ragni, A.
    Gales, M. J. F.
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 4788 - 4791
  • [39] Deep Scattering Power Spectrum Features for Robust Speech Recognition
    Joy, Neethu M.
    Oglic, Dino
    Cvetkovic, Zoran
    Bell, Peter
    Renals, Steve
    INTERSPEECH 2020, 2020, : 1673 - 1677
  • [40] A robust speech analysis in speech recognition
    Miyanaga, Y
    Gozen, S
    Ohtsuki, N
    2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 706 - 709
12345