ISCA Archive Interspeech 2009
ISCA Archive Interspeech 2009

Improving speech understanding accuracy with limited training data using multiple language models and multiple understanding models

Masaki Katsumaru, Mikio Nakano, Kazunori Komatani, Kotaro Funakoshi, Tetsuya Ogata, Hiroshi G. Okuno

We aim to improve a speech understanding module with a small amount of training data. A speech understanding module uses a language model (LM) and a language understanding model (LUM). A lot of training data are needed to improve the models. Such data collection is, however, difficult in an actual process of development. We therefore design and develop a new framework that uses multiple LMs and LUMs to improve speech understanding accuracy under various amounts of training data. Even if the amount of available training data is small, each LM and each LUM can deal well with different types of utterances and more utterances are understood by using multiple LM and LUM. As one implementation of the framework, we develop a method for selecting the most appropriate speech understanding result from several candidates. The selection is based on probabilities of correctness calculated by logistic regressions. We evaluate our framework with various amounts of training data.


doi: 10.21437/Interspeech.2009-699

Cite as: Katsumaru, M., Nakano, M., Komatani, K., Funakoshi, K., Ogata, T., Okuno, H.G. (2009) Improving speech understanding accuracy with limited training data using multiple language models and multiple understanding models. Proc. Interspeech 2009, 2735-2738, doi: 10.21437/Interspeech.2009-699

@inproceedings{katsumaru09_interspeech,
  author={Masaki Katsumaru and Mikio Nakano and Kazunori Komatani and Kotaro Funakoshi and Tetsuya Ogata and Hiroshi G. Okuno},
  title={{Improving speech understanding accuracy with limited training data using multiple language models and multiple understanding models}},
  year=2009,
  booktitle={Proc. Interspeech 2009},
  pages={2735--2738},
  doi={10.21437/Interspeech.2009-699}
}