In this paper, the problem of text-to-phoneme mapping of isolated words for the English language is studied. Multilayer perceptron, recurrent and bidirectional recurrent neural network architectures are compared in the text-to-phoneme mapping task. Multilayer perceptron neural networks utilize contextual information due to the orthography of a word. In our study, recurrent and bidirectional recurrent neural networks, on the other hand, do not take the letter context into account. Instead, these networks utilize the contextual information due to the previously transcribed phonemes as introduced by the feedback loop in the networks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A study on different neural network architectures applied to text-to-phoneme mapping


    Contributors:
    Bilcu, E.B. (author) / Suontausta, J. (author) / Saarinen, J. (author)


    Publication date :

    2003-01-01


    Size :

    340207 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Study on Different Neural Network Architectures Applied to Text-to-Phoneme Mapping

    Bilcu, E. B. / Suontausta, J. / Saarinen, J. et al. | British Library Conference Proceedings | 2003


    A Hybird Neural Network/Rule Based Architecture Used as a Text to Phoneme Transcriber

    Gubbins, P. R. / Curtis, K. M. / Burniston, J. D. et al. | British Library Conference Proceedings | 1994