We present a portable platform for spoken dialogue systems. Conventional development of speech interfaces involves much labor cost in either describing a task grammar or collecting a task corpus. Our platform automatically generates a lexicon and a language model of keyphrases based on task description and the domain database. By spotting key-phrases using both the generated grammar and word 2-gram model trained with dialogue corpora of similar domains, we realize flexible speech understanding on a variety of utterances. Furthermore, adopting a GUI that explicitly displays acceptable utterance patterns is effective in guiding user utterances within the system's capability. We evaluate the generated system using 24 novice users. The number of unacceptable utterances are significantly reduced with the simple phrase grammar and GUI. And the phrase spotter using the combined language model improves the semantic accuracy by 15.5% compared with the conventional method decoding the whole sentence with a fixed grammar.
Cite as: Komatani, K., Tanaka, K., Kashima, H., Kawahara, T. (2001) Domain-independent spoken dialogue platform using key-phrase spotting based on combined language model. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1319-1322, doi: 10.21437/Eurospeech.2001-341
@inproceedings{komatani01_eurospeech,
author={Kazunori Komatani and Katsuaki Tanaka and Hiroaki Kashima and Tatsuya Kawahara},
title={{Domain-independent spoken dialogue platform using key-phrase spotting based on combined language model}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1319--1322},
doi={10.21437/Eurospeech.2001-341}
}