Showing papers by "Shuji Doshita published in 1999"

Topic independent language model for key-phrase detection and verification

Abstract: A topic independent lexical and language modeling for robust key-phrase detection and verification is presented. Instead of assuming a domain specific lexicon and language model, our model is designed to characterize filler phrases depending on the speaking-style, thus can be trained with large corpora of different topics but the same style. Mutual information criterion is used to select topic independent filler words and their N-gram model is used for verification of key-phrase hypotheses. A dialogue-style dependent filler model improves the key-phrase detection in different dialogue applications. A lecture-style dependent model is trained with transcriptions of various oral presentations by filtering out topic specific words. It performs much better verification of key-phrases uttered during lectures of different topics compared with the conventional syllable-based model and large vocabulary model.

The use of duration similarity templates in speech rhythm training

Abstract: We present a novel method of speech rhythm training for a mora-timed language. Previous works were mainly concerned with a case-by-case training. In this work we devise "duration templates" describing a set of words with similar speech rhythm and then apply them to training speech rhythms of learners. Especially, in this system each mora is measured by the ratio of its duration to the whole duration of a word, not by absolute millisecond measurement.