<link rel="stylesheet" href="styles.cf390c6bfbe7555f.css">

學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Author: search.filters.author.CHEN, SHSubject: search.filters.subject.SPEECH RECOGNITION

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item type:Item,
    ISOLATED MANDARINE SYLLABLE RECOGNITION USING SEGMENTAL FEATURES
    (1995-02-01)
    CHANG, S
    ;
    CHEN, SH
    ;
    電信工程研究所
    ;
    電信研究中心
    ;
    Institute of Communications Engineering
    A segment-based speech recognition scheme is proposed. The basic idea is to model explicitly the correlation among successive frames of speech signals by using features representing contours of spectral parameters. The speech signal of an utterance is regarded as a template formed by directly concatenating a sequence of acoustic segments. Each constituent acoustic segment is of variable length in nature and represented by a fixed dimensional feature vector formed by coefficients of discrete orthonormal polynomial expansions for approximating its spectral parameter contours. In the training, an automatic algorithm is proposed to generate several segment-based reference templates for each syllable class. In the testing, a frame-based dynamic programming procedure is employed to calculate the matching score of comparing the test utterance with each reference template. Performance of the proposed scheme was examined by simulations on multispeaker speech recognition for 408 highly confusing isolated Mandarin base-syllables. A recognition rate of 81.1% was achieved for the case using 5-segment, 8-reference template models with cepstral and delta-cepstral coefficients as recognition features. It is 4.5% higher than that of a well-modelled 12-state, 5-mixture CHMM method using cepstral, delta cepstral, and delta-delta cepstral coefficients.
  • Thumbnail Image
    Item type:Item,
    SPEAKER-INDEPENDENT MANDARINE PLOSIVE RECOGNITION WITH DYNAMIC FEATURES AND MULTILAYER PERCEPTRONS
    (1995-02-16)
    CHEN, WY
    ;
    CHEN, SH
    ;
    交大名義發表
    ;
    電信工程研究所
    ;
    National Chiao Tung University
    A new method for recognising plosives in isolated Mandarin syllables is discussed in the Letter. After automatically detecting the plosive segment of the input utterance, some dynamic features are extracted from its spectral parameter contours using orthonormal polynomial transforms. Next, an MLP trained with an algorithm based on a minimum error criterion is employed to distinguish plosives using these features. A promising recognition rare of 73.6% is achieved in a speaker-independent test using a database containing utterances of 110 syllables uttered by 100 speakers.
  • Thumbnail Image
    Item type:Item,
    SPEECH RECOGNITION WITH HIERARCHICAL RECURRENT NEURAL NETWORKS
    (1995-06-01)
    CHEN, WY
    ;
    LIAO, YF
    ;
    CHEN, SH
    ;
    交大名義發表
    ;
    電信工程研究所
    A hierarchical recurrent neural network (HRNN)for speech recognition is presented. The HRNN is trained by a generalized probabilistic descent (GPD) algorithm. Consequently, the difficulty of empirically selecting an appropriate target function for training RNNs can be avoided. Results obtained in this study indicate the proposed HRNN has the advantages of being capable of absorbing the temporal variation of speech patterns as well as possessing effective discrimination capabilities. The scaling problem of RNNs is also greatly reduced. Additionally, a realization of the system using initial/final sub-syllable models for isolated Mandarin syllable recognition is also undertaken for verifying its effectiveness. The effectiveness of the proposed HRNN is confirmed by the experimental results.
  • Thumbnail Image
    Item type:Item,
    IMPROVED SYLLABLE-BASED CONTINUOUS MANDARINE SPEECH RECOGNITION USING INTERSYLLABLE BOUNDARY MODELS
    (1995-05-25)
    CHANG, S
    ;
    CHEN, SH
    ;
    電信工程研究所
    ;
    電信研究中心
    ;
    Institute of Communications Engineering
    A novel approach to compensate for the intersyllable coarticulation effect on continuous Mandarin speech recognition by supplementing the syllable HMM models with intersyllable boundary models is proposed. Experimental results show that the syllable recognition errors of a speaker-dependent recognition task are reduced by 24%.