Invariant-integration method for robust feature extraction in speaker-independent speech recognition

被引：0
|
作者：
Mueller, Florian [1 ]
Mertins, Alfred [1 ]
机构：
[1] Univ Lubeck, Inst Signal Proc, Lubeck, Germany
来源：
INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | 2009年
关键词：
speech recognition; speaker-independency; invariant integration; monomials; HIDDEN MARKOV-MODELS; NORMALIZATION; TRANSFORM;
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：
The vocal tract length (VTL) is one of the variabilities that speaker-independent automatic speech recognition (ASR) systems encounter. Standard methods to compensate for the effects of different VTLs within the processing stages of the ASR systems often have a high computational effort. By using an appropriate warping scheme for the frequency centers of the time-frequency analysis, a change in VTL can be approximately described by a translation in the subband-index space. We present a new type of features that is based on the principle of invariant integration, and an according feature selection method is described. ASR experiments show the increased robustness of the proposed features in comparison to standard MFCCs.
引用
收藏
页码：2939 / 2942
页数：4
相关论文
共 50 条
  • [21] Uighur speaker-independent speech recognition based on CDCPM
    Wang, K.L.
    2001, Science Press (38):
  • [22] On Speaker-Independent, Speaker-Dependent, and Speaker-Adaptive Speech Recognition
    Huang, Xuedong
    Lee, Kai-Fu
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1993, 1 (02): : 150 - 157
  • [23] Speaker adaptation techniques for speech recognition with a speaker-independent phonetic recognizer
    Kim, WG
    Jang, M
    COMPUTATIONAL INTELLIGENCE AND SECURITY, PT 1, PROCEEDINGS, 2005, 3801 : 95 - 100
  • [24] Speaker-independent Speech Emotion Recognition Based on Random Forest Feature Selection Algorithm
    Cao, Wei-Hua
    Xu, Jian-Ping
    Liu, Zhen-Tao
    PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 10995 - 10998
  • [25] SPEAKER-CONSISTENT PARSING FOR SPEAKER-INDEPENDENT CONTINUOUS SPEECH RECOGNITION
    YAMAGUCHI, K
    SINGER, H
    MATSUNAGA, S
    SAGAYAMA, S
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1995, E78D (06) : 719 - 724
  • [26] Language and Speaker-Independent Feature Transformation for End-to-End Multilingual Speech Recognition
    Hayakawa, Tomoaki
    Leow, Chee Siang
    Kobayashi, Akio
    Utsuro, Takehito
    Nishizaki, Hiromitsu
    INTERSPEECH 2021, 2021, : 2431 - 2435
  • [27] A method of joint compensation of additive and convolutive distortions for speaker-independent speech recognition
    Gong, YF
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2005, 13 (05): : 975 - 983
  • [28] An Auditory Feature Extraction Method for Robust Speaker Recognition
    Hu, Fengsong
    Cao, Xiaoyu
    PROCEEDINGS OF 2012 IEEE 14TH INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGY, 2012, : 1067 - 1071
  • [29] Acoustic-phonetic speech parameters for speaker-independent speech recognition
    Deshmukh, O
    Espy-Wilson, CY
    Juneja, A
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 593 - 596
  • [30] Speech recognition as feature extraction for speaker recognition
    Stolcke, A.
    Shriberg, E.
    Ferrer, L.
    Kajarekar, S.
    Sonmez, K.
    Tur, G.
    2007 IEEE WORKSHOP ON SIGNAL PROCESSING APPLICATIONS FOR PUBLIC SECURITY AND FORENSICS, 2007, : 39 - +
12345