11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Improved Spoken Term Detection by Discriminative Training of Acoustic Models Based on User Relevance Feedback

Hung-yi Lee, Chia-ping Chen, Ching-feng Yeh, Lin-shan Lee

National Taiwan University, Taiwan

In a previous paper, we proposed a new framework for spoken term detection by exploiting user relevance feedback information to estimate better acoustic model parameters to be used in rescoring the spoken segments. In this way, the acoustic models can be trained with a criterion of better retrieval performance, and the retrieval performance can be less dependent on the existence of a set of acoustic models well matched to the corpora to be retrieved. In this paper, a new set of objective functions for acoustic model training in the above framework was proposed considering the nature of retrieval process and its performance measure, and discriminative training algorithms maximizing the objective functions were developed. Significant performance improvements were obtained in preliminary experiments.

Full Paper

Bibliographic reference.  Lee, Hung-yi / Chen, Chia-ping / Yeh, Ching-feng / Lee, Lin-shan (2010): "Improved spoken term detection by discriminative training of acoustic models based on user relevance feedback", In INTERSPEECH-2010, 1273-1276.