Investigating data selection for minimum phone error training of acoustic models

Shih Hung Liu*, Fang Hui Chu, Shih Hsiang Lin, Berlin 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

7 引文 斯高帕斯(Scopus)

摘要

This paper considers minimum phone error (MPE) Dased discriminative training of acoustic models for Mandarin broadcast news recognition. A novel data selection approach based on the normalized frame-level entropy of Gaussian posterior probabilities obtained from the word lattice of the training utterance was explored. It has the merit of making the training algorithm focus much more on the training statistics of those frame samples that center nearly around the decision boundary for better discrimination. Moreover, we presented a new phone accuracy function based on the frame-level accuracy of hypothesized phone arcs instead of using the raw phone accuracy function of MPE training. The underlying characteristics of the presented approaches were extensively investigated and their performance was verified by comparison with the original MPE training approach. Experiments conducted on the broadcast news collected in Taiwan showed that the integration of the frame-level data selection and accuracy calculation could achieve slight but consistent improvements over the baseline system.

原文英語
主出版物標題Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007
頁面348-351
頁數4
出版狀態已發佈 - 2007 十二月 1
事件IEEE International Conference onMultimedia and Expo, ICME 2007 - Beijing, 中国
持續時間: 2007 七月 22007 七月 5

出版系列

名字Proceedings of the 2007 IEEE International Conference on Multimedia and Expo, ICME 2007

其他

其他IEEE International Conference onMultimedia and Expo, ICME 2007
國家/地區中国
城市Beijing
期間2007/07/022007/07/05

ASJC Scopus subject areas

  • 電腦繪圖與電腦輔助設計
  • 軟體

指紋

深入研究「Investigating data selection for minimum phone error training of acoustic models」主題。共同形成了獨特的指紋。

引用此