Recurrent neural networks (RNNs) can be used to handle sequential patterns and have been used for speech recognition. To overcome the shortcomings of RNN, recurrent sub neural networks (RSNNs) are used, where an RSNN is built independently for each class. The training algorithm of the RSNN is based on the backpropagation algorithm. Speaker dependent connected Chinese digit-speech recognition experiments were carried out. Some factors influencing the performance of RSNNs have been studied. The experiments show that RSNN is easier to train and gives higher performance than RNN.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Recurrent sub neural networks applied to speech recognition


    Contributors:
    Wei-Ying Li (author) / Xiao-Mei Tang (author) / Ke-Chu Yi (author) / Zheng Hu (author)


    Publication date :

    1994-01-01


    Size :

    328232 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Recurrent Sub Neural Networks Applied to Speech Recognition

    Li, W. Y. / Tang, X. M. / Yi, K. C. et al. | British Library Conference Proceedings | 1994


    Visual speech recognition by recurrent neural networks

    Rabi, G. / Si Wei Lu | British Library Online Contents | 1998


    Pose Based Action Recognition of Vulnerable Road Users Using Recurrent Neural Networks

    Kress, Viktor / Schreck, Steven / Zernetsch, Stefan et al. | IEEE | 2020



    Parallel Neural Networks for Speaker-Independent All-Chinese-Syllable Speech Recognition

    Fang, D. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994