Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features

Yi Fen Liu*, Shu Chuan Tseng, J. S.Roger Jang, C. H.Alvin Chen

*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

Continuous speech input for ASR processing is usually presegmented into speech stretches by pauses. In this paper, we propose that smaller, prosodically defined units can be identified by tackling the problem on imbalanced prosodic unit boundary detection using five machine learning techniques. A parsimonious set of linguistically motivated prosodic features has been proven to be useful to characterize prosodic boundary information. Furthermore, BMPM is prone to have true positive rate on the minority class, i.e. the defined prosodic units. As a whole, the decision tree classifier, C4.5, reaches a more stable performance than the other algorithms.

原文英語
主出版物標題Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010
發行者International Speech Communication Association
頁面1417-1420
頁數4
出版狀態已發佈 - 2010
對外發佈

出版系列

名字Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010

ASJC Scopus subject areas

  • 語言與語言學
  • 言語和聽力

指紋

深入研究「Coping imbalanced prosodic unit boundary detection with linguistically-motivated prosodic features」主題。共同形成了獨特的指紋。

引用此