Statistical language model adaptation for Mandarin broadcast news transcription

Berlin Chen*, Wen Hung Tsai, Jen Wei Kuo

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

4 引文 斯高帕斯(Scopus)

摘要

This paper investigates statistical language model adaptation for Mandarin broadcast news transcription. A topical mixture model was proposed to explore the long-span latent topical information for dynamic language model adaptation. The underlying characteristics and various kinds of model complexities were extensively investigated, while their performance was verified by comparison with the conventional MAP-based adaptation approaches, which are devoted to extracting the short-span n-gram information. The speech recognition experiments were conducted on the broadcast news collected in Taiwan. Very promising results in both perplexity and word error rate reductions were initially obtained.

原文英語
主出版物標題2004 International Symposium on Chinese Spoken Language Processing - Proceedings
頁面313-316
頁數4
出版狀態已發佈 - 2004 十二月 1
事件2004 International Symposium on Chinese Spoken Language Processing - Hong Kong, China, 香港
持續時間: 2004 十二月 152004 十二月 18

出版系列

名字2004 International Symposium on Chinese Spoken Language Processing - Proceedings

其他

其他2004 International Symposium on Chinese Spoken Language Processing
國家/地區香港
城市Hong Kong, China
期間2004/12/152004/12/18

ASJC Scopus subject areas

  • 工程 (全部)

指紋

深入研究「Statistical language model adaptation for Mandarin broadcast news transcription」主題。共同形成了獨特的指紋。

引用此