Information source extension is utilized to improve the language model for large vocabulary continuous speech recognition (LVCSR). McMillan's theory, source extension make the model entropy close to the real source entropy, implies that the better language model can be obtained by source extension (making new unit through word concatenations and using the new unit for the language modeling). In this paper, we examined the effectiveness of this source extension. Here, we tested two methods of source extension: frequency-based extension and entropy-based extension. We tested the effect in terms of perplexity and recognition accuracy using Mainichi newspaper articles and IN AS speech corpus. As the results, the bi-gram perplexity is improved from 98.6 to 70.8 and tri-gram perplexity is improved from Jt1.9 to 26.4- The bigram-based recognition accuracy is improved from 79.8% to 85.3%.
|出版ステータス||Published - 1998|
|イベント||5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, Australia|
継続期間: 1998 11月 30 → 1998 12月 4
|Conference||5th International Conference on Spoken Language Processing, ICSLP 1998|
|Period||98/11/30 → 98/12/4|
ASJC Scopus subject areas