Skip to Main Content
To enhance the robustness of speech segmentation, this paper presents the improved segmentation model based on Bayesian method which combined with a prior probability which is independent to noise feature as the compensation for the mismatch of acoustic model. We evaluated and compared the performance of different methods in speech segmentation experiment.
Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on (Volume:2 )
Date of Conference: 14-17 Dec. 2003