A neural network using acoustic sub-word units for continuous speech recognition

被引：0
|
作者：
Yu, HJ
Oh, YH
机构：
来源：
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 | 1996年
关键词：
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
A subword-based neural network model for continuous speech recognition is proposed. The system consists of three modules, and each module is composed of simple neural networks. The speech input is segmented into non-uniform units by the network in the first module. Non-uniform unit can model phoneme variations which spread for several phonemes and between words. The second module recognizes segmented units. The unit has stationary and transition parts, and the network is divided according to the two parts. The last module spots words by modeling temporal representation. The results of speaker independent word spotting of 520 words are described.
引用
收藏
页码：506 / 509
页数：4
相关论文
共 50 条
  • [1] A neural network for 500 vocabulary word spotting using acoustic sub-word units
    Yu, HJ
    Oh, YH
    [J]. 1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 3277 - 3280
  • [2] Speech recognition using sub-word units dependent on phonetic contexts of both training and recognition vocabularies
    Hattori, H
    Yamada, E
    [J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2309 - 2312
  • [3] Sub-word Based Offline Handwritten Farsi Word Recognition Using Recurrent Neural Network
    Ghadikolaie, Mohammad Fazel Younessy
    Kabir, Ehsanolah
    Razzazi, Farbod
    [J]. ETRI JOURNAL, 2016, 38 (04) : 703 - 713
  • [4] Word/sub-word lattices decomposition and combination for speech recognition
    Le, Viet-Bac
    Seng, Sopheap
    Besacier, Laurent
    Bigi, Brigitte
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4321 - 4324
  • [5] Combining multiple-sized sub-word units in a speech recognition system using baseform selection
    Nagarajan, T.
    Vijayalakshmi, P.
    O'Shaughnessy, Douglas
    [J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1595 - 1597
  • [6] Incorporating language constraints in sub-word based speech recognition
    Erdogan, H
    Büyük, O
    Oflazer, K
    [J]. 2005 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2005, : 98 - +
  • [7] Natural Sounding Sub-word Units Concatenation in Malay Speech Synthesis
    Tiun, Sabrina
    Abdullah, Rosni
    Kong, Tang Enya
    [J]. PROCEEDINGS OF THE 2009 INTERNATIONAL CONFERENCE ON SIGNAL ACQUISITION AND PROCESSING, 2009, : 77 - +
  • [8] Printed Arabic sub-word recognition using moments
    Elrube, Ibrahim A.
    El Sonni, Mohamed T.
    Saleh, Soha S.
    [J]. World Academy of Science, Engineering and Technology, 2010, 42 : 724 - 728
  • [9] Language identification using parallel sub-word recognition
    Jayram, AKVS
    Ramasubramanian, V
    Sreenivas, TV
    [J]. 2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING I, 2003, : 32 - 35
  • [10] Sub-Word Unit based Non-Audible Speech Recognition using Surface Electromyography
    Walliczek, Matthias
    Kraft, Florian
    Jou, Szu-Chen
    Schultz, Tanja
    Waibel, Alex
    [J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1487 - +
12345