A Feature Extraction Method for Automatic Speech Recognition Based on the Cochlear Nucleus

被引：0
|
作者：
Haque, Serajul [1 ]
Togneri, Roberto [1 ]
机构：
[1] Univ Western Australia, Sch Elect Elect & Comp Engn, Nedlands, WA 6009, Australia
来源：
11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4 | 2010年
关键词：
Speech recognition; zero-crossings; auditory model; cochlear nucleus; hidden Markov model;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Motivated by the human auditory system, a feature extraction method for automatic speech recognition (ASR) based on the differential processing strategy of the AVCN, PVCN and the DCN of the cochlear nucleus is proposed. The method utilizes a zero-crossing with peak amplitudes (ZCPA) auditory model as synchrony detector to discriminate the low frequency formants. It utilizes the mean rate information in the synapse processing to capture the very rapidly changing dynamic nature of speech. Additionally, a temporal companding method is utilized for spectral enhancement through two-tone suppression. We propose to separate synchrony detection from synaptic processing as observed in the parallel processing methodology in the cochlear nucleus. HMM recognition using isolated digits showed improved recognition rates in clean and in non-stationary noise conditions than the existing auditory model.
引用
收藏
页码：2454 / 2457
页数：4
相关论文
共 50 条
  • [1] Feature extraction for automatic speech recognition (ASR)
    Swartz, B
    Magotra, N
    [J]. THIRTIETH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, 1997, : 748 - 751
  • [2] Synchrony-Based Feature Extraction for Robust Automatic Speech Recognition
    de-La-Calle-Silos, Fernando
    Stern, Richard M.
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (08) : 1158 - 1162
  • [3] Feature Extraction Method Human Factor Cepstral Coefficients in Automatic Speech Recognition
    Rahali, Hajer
    Hajaiej, Zied
    Ellouze, Noureddine
    [J]. 2014 9TH INTERNATIONAL SYMPOSIUM ON COMMUNICATION SYSTEMS, NETWORKS & DIGITAL SIGNAL PROCESSING (CSNDSP), 2014, : 266 - 270
  • [4] Soft Margin Feature Extraction for Automatic Speech Recognition
    Li, Jinyu
    Lee, Chin-Hui
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 293 - 296
  • [5] Feature Extraction Based on Speech Attractors in the Reconstructed Phase Space for Automatic Speech Recognition Systems
    Shekofteh, Yasser
    Almasganj, Farshad
    [J]. ETRI JOURNAL, 2013, 35 (01) : 100 - 108
  • [6] Robust speech recognition method based on discriminative environment feature extraction
    Han, JQ
    Gao, W
    [J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2001, 16 (05) : 458 - 464
  • [7] A new speaker recognition method based on the reliability of speech feature extraction
    Yang, Z
    Li, CW
    Zhang, LH
    [J]. 6TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL IV, PROCEEDINGS: MOBILE/WIRELESS COMPUTING AND COMMUNICATION SYSTEMS I, 2002, : 168 - 172
  • [8] Robust Speech Recognition Method Based on Discriminative Environment Feature Extraction
    韩纪庆
    高文
    [J]. Journal of Computer Science & Technology, 2001, (05) : 458 - 464
  • [9] A Feature Extraction Method based on Combined Wavelets Filter in Speech Recognition
    Zhang, Xueying
    Sun, Ying
    Hou, Wenjun
    [J]. 2008 IEEE CONFERENCE ON CYBERNETICS AND INTELLIGENT SYSTEMS, VOLS 1 AND 2, 2008, : 1236 - +
  • [10] Robust speech recognition method based on discriminative environment feature extraction
    Jiqing Han
    Wen Gao
    [J]. Journal of Computer Science and Technology, 2001, 16 : 458 - 464
12345