Statistical language models for large vocabulary spontaneous speech recognition in dutch

@inproceedings{Duchateau2005StatisticalLM,
  title={Statistical language models for large vocabulary spontaneous speech recognition in dutch},
  author={Jacques Duchateau and Dong Hoon Van Uytsel and Hugo Van hamme and Patrick Wambacq},
  booktitle={INTERSPEECH},
  year={2005}
}
In state-of-the-art large vocabulary automatic recognition systems, a large statistical language model is used, typically an N-gram. However in order to estimate this model, a large database of sentences or texts in the same style as the recognition task is needed. For spontaneous speech one doesn’t dispose of such database since it should consist of… CONTINUE READING