Although there have been regular improvements in speech recognition technology over the past decade, speech recognition is far from being a solved problem. Recognition systems are usually tuned to a particular task and porting the system to a new task (or language) is both timeconsuming and expensive. In this paper, issues in speech recognizer portability are addressed through the development of generic core speech recognition technology. First, the genericity of wide domain models is assessed by evaluating performance on several tasks. Then, the use of transparent methods for adapting generic models to a specific taskis explored. Finally, further techniques are evaluated aiming at enhancing the genericity of the wide domain models. We show that unsupervised acoustic model adaptation and multi-source training can reduce the performance gap between task-independent and task-dependent acoustic models, and for some tasks even out-perform task-dependent acoustic models.
Cite as: Lefevre, F., Gauvain, J.-L., Lamel, L. (2001) Improving genericity for task-independent speech recognition. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1241-1244, doi: 10.21437/Eurospeech.2001-322
@inproceedings{lefevre01_eurospeech,
author={Fabrice Lefevre and Jean-Luc Gauvain and Lori Lamel},
title={{Improving genericity for task-independent speech recognition}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1241--1244},
doi={10.21437/Eurospeech.2001-322}
}