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

@inproceedings{Steidl2003ImprovingCS,
  title={Improving Children's Speech Recognition by HMM Interpolation with an Adults' Speech Recognizer},
  author={Stefan Steidl and Georg Stemmer and Christian Hacker and Elmar N{\"o}th and Heinrich Niemann},
  booktitle={DAGM-Symposium},
  year={2003}
}

• Stefan Steidl, Georg Stemmer, +2 authors Heinrich Niemann
• Published in DAGM-Symposium 2003
• DOI:10.1007/978-3-540-45243-0_76

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

View via Publisher

Alternate Sources

Save to Library

Create Alert

Cite