Two-Level Phoneme Recognition Based on Successive Use of Monophone and Diphone Models

Panu Somervuo

    Research output: Working paperProfessional

    Original languageEnglish
    Publication statusPublished - 2002
    MoE publication typeD4 Published development or research report or study

    Publication series

    NameEUSIPCO, XI European Signal Processing Conference, Sept. 3-6, 2002, Toulouse, France

    Keywords

    • hidden Markov model
    • learning vector quantization
    • multi-level pattern recognition
    • speech recognition

    Cite this