Speaker-independent speech recognition by means of functional-link neural networks

被引：0
|
作者：
Ugena, A
de Arriaga, F
El Alami, M
机构：
来源：
15TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 2, PROCEEDINGS: PATTERN RECOGNITION AND NEURAL NETWORKS | 2000年
关键词：
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 purpose of the paper is to show the improvements so far obtained in the solution of the speech recogntion problem by means of functional-link neural networks (1). The specific problem deals with the speaker independent recognition of the spanish vowels, a problem of theoretical and practical complexity. The voice Fourier spectrum has been obtained and from it the Mel-Cepstrum and Cepstrum coefficients, which have been used as inputs for the neural architecture in charge of the recognition problem. Different polynomial functions such as Newton and Lagrange developments are used as functional expansions of the network. The results so far obtained show improvements in the recognition rate in all cases with respect to those obtained with the multilayer perceptron.
引用
收藏
页码：1018 / 1021
页数：2
相关论文
共 50 条
  • [21] SPEAKER-INDEPENDENT CONSONANT CLASSIFICATION IN CONTINUOUS SPEECH WITH DISTINCTIVE FEATURES AND NEURAL NETWORKS
    DEMORI, R
    FLAMMIA, G
    JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1993, 94 (06): : 3091 - 3103
  • [22] ITERATIVE DEEP NEURAL NETWORKS FOR SPEAKER-INDEPENDENT BINAURAL BLIND SPEECH SEPARATION
    Liu, Qingju
    Xu, Yong
    Jackson, Philip J. B.
    Wang, Wenwu
    Coleman, Philip
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 541 - 545
  • [23] 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
  • [24] SPEAKER-INDEPENDENT WORD RECOGNITION IN CONNECTED SPEECH ON THE BASIS OF PHONEME RECOGNITION
    MAENOBU, K
    ARIKI, Y
    SAKAI, T
    INFORMATION SCIENCES, 1984, 33 (1-2) : 31 - 61
  • [25] Across-speaker Articulatory Normalization for Speaker-independent Silent Speech Recognition
    Wang, Jun
    Samal, Ashok
    Green, Jordan R.
    15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 1179 - 1183
  • [26] An automatic speech recognition system with speaker-independent identification support
    Caranica, Alexandru
    Burileanu, Corneliu
    ADVANCED TOPICS IN OPTOELECTRONICS, MICROELECTRONICS, AND NANOTECHNOLOGIES VII, 2015, 9258
  • [27] ON LARGE-VOCABULARY SPEAKER-INDEPENDENT CONTINUOUS SPEECH RECOGNITION
    LEE, KF
    SPEECH COMMUNICATION, 1988, 7 (04) : 375 - 379
  • [28] Speaker-independent telephone speech recognition system: the VCS TeleRec
    Hunt, Alan
    Speech technology, 1988, 4 (02): : 80 - 82
  • [29] A SPEAKER-INDEPENDENT SPEECH RECOGNITION SYSTEM FOR TELEPHONE NETWORK APPLICATIONS
    TRNKA, R
    REVUE TECHNIQUE THOMSON-CSF, 1984, 16 (04): : 847 - 861
  • [30] Speaker-independent speech recognition based on tree-structured speaker clustering
    Kosaka, T
    Matsunaga, S
    Sagayama, S
    COMPUTER SPEECH AND LANGUAGE, 1996, 10 (01): : 55 - 74
12345