Improving Children's Speech Recognition by HMM Interpolation with an Adults' Speech Recognizer

  title={Improving Children's Speech Recognition by HMM Interpolation with an Adults' Speech Recognizer},
  author={S. Steidl and G. Stemmer and C. Hacker and E. N{\"o}th and H. Niemann},
  • S. Steidl, G. Stemmer, +2 authors H. Niemann
  • Published in DAGM-Symposium 2003
  • Computer Science
  • In this paper we address the problem of building a good speech recognizer if there is only a small amount of training data available. The acoustic models can be improved by interpolation with the well-trained models of a second recognizer from a different application scenario. In our case, we interpolate a children’s speech recognizer with a recognizer for adults’ speech. Each hidden Markov model has its own set of interpolation partners; experiments were conducted with up to 50 partners. The… CONTINUE READING
    19 Citations
    Towards age-independent acoustic modeling
    • 26
    • PDF
    A survey about databases of children's speech
    • 9
    • PDF
    Automatic assessment of children speech to support language learning
    • 6
    • PDF
    Adaptation in the pronunciation space for non-native speech recognition
    • 26
    • PDF
    Acoustic model adaptation using in-domain background models for dysarthric speech recognition
    • 36
    • PDF
    Improving ASR performance using context-dependent phoneme models
    • 4


    Analysis and modeling of non-native speech for automatic speech recognition
    • 39
    Verbmobil: Foundations of Speech-to-Speech Translation
    • 761
    • PDF
    Automatische Spracherkennung - Grundlagen, statistische Modelle und effiziente Algorithmen
    • 49
    Interpolated estimation of Markov source parameters from sparse data
    • 997
    Interpolation von Hidden Markov Modellen
    • Diploma Thesis (in German), Chair for Pattern Recognition, University of Erlangen-Nuremberg
    • 2002
    Interpolation von Hidden Markov Modellen. Diploma Thesis
    • Interpolation von Hidden Markov Modellen. Diploma Thesis
    • 2002
    SAMPA – Computer Readable Phonetic Alphabet
    • Recognizing Non – Native Speech : Characterizing and Adapting to Non – Native Usage in LVCSR
    • 2001
    Zürcher Lesetest
    • 6th edn. Testzentrale Göttingen, Robert-Bosch-Breite
    • 2000