N-best based supervised and unsupervised adaptation for native and non-native speakers in cars

P. Nguyen*, Ph Gelin, J. C. Junqua, Jen-Tzung Chien

*此作品的通信作者

研究成果: Conference article同行評審

14 引文 斯高帕斯(Scopus)

摘要

In this paper, a new set of techniques exploiting N-best hypotheses in supervised and unsupervised adaptation are presented. These techniques combine statistics extracted from the N-best hypotheses with a weight derived from a likelihood ratio confidence measure. In the case of supervised adaptation the knowledge of the correct string is used to perform N-best based corrective adaptation. Experiments run for continuous letter recognition recorded in a car environment show that weighting N-best sequences by a likelihood ratio confidence measure provides only marginal improvement as compared to 1-best unsupervised adaptation and N-best unsupervised adaptation with equal weighting. However, an N-best based supervised corrective adaptation method weighting correct letters positively and incorrect letters negatively, resulted in a 13% decrease of the error rate as compared with supervised adaptation. The largest improvement was obtained for non-native speakers.

原文English
頁(從 - 到)173-176
頁數4
期刊ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
1
DOIs
出版狀態Published - 1 一月 1999
事件Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) - Phoenix, AZ, USA
持續時間: 15 三月 199919 三月 1999

指紋

深入研究「N-best based supervised and unsupervised adaptation for native and non-native speakers in cars」主題。共同形成了獨特的指紋。

引用此