The applicability of adaptive language modelling for the broadcast news task

Adaptive language models have consistently been shown to lead to a significant reduction in language model perplexity compared to the equivalent static trigram model on many data sets. When these language models have been applied to speech recognition, however, they have seldom resulted in a corresponding reduction in word error rate. This paper will investigate some of the possible reasons for this apparent discrepancy, and will explore the circumstances under which adaptive language models can be useful. We will concentrate on cache-based and mixture-based models and their use on the Broadcast News task.

[1]  Dietrich Klakow,et al.  Language model adaptation using dynamic marginals , 1997, EUROSPEECH.

[2]  Steve R. Waterhouse,et al.  Transcription of broadcast television and radio news: the 1996 ABBOT system , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Mari Ostendorf,et al.  Analyzing and predicting language model improvements , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[4]  Renato De Mori,et al.  A Cache-Based Natural Language Model for Speech Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Ronald Rosenfeld,et al.  Using story topics for language model adaptation , 1997, EUROSPEECH.

[6]  Stanley F. Chen,et al.  Evaluation Metrics For Language Models , 1998 .

[7]  Hermann Ney,et al.  Adaptive topic - dependent language modelling using word - based varigrams , 1997, EUROSPEECH.

[8]  Anthony J. Robinson,et al.  Language model adaptation using mixtures and an exponentially decaying cache , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.