Hybrid Training Method for Tied Mixture Density Hidden Markov Models Using Learning Vector Quantization and Viterbi Estimation

    Research output: Working paperProfessional

    7 Citations (Scopus)
    Original languageEnglish
    Pages362-371
    Publication statusPublished - 1994
    MoE publication typeD4 Published development or research report or study

    Publication series

    NameIEEE Workshop on Neural Networks for Signal Processing, Ermioni, Greece, September 1994

    Keywords

    • learning vector quantization
    • semi-continuous hidden Markov model
    • speech recognition

    Cite this