We introduce a new noise suppression method by using a search strategy with multi-model compositions that includes the following models: speech, noise, and their composites. Before noise suppression, a beam search is performed to find the best sequences of these models using noise acoustic models, noise-label n-gram models, and a noise-label lexicon. Noise suppression is frame-synchronously performed by the multiple models selected by the search. We evaluated this method using the E-Nightingale task, which contains voice memoranda spoken by nurses during actual work at hospitals. For this difficult task, the proposed method obtained a 21.6% error reduction rate.
Cite as: Jitsuhiro, T., Toriyama, T., Kogure, K. (2007) Noise suppression using search strategy with multi-model compositions. Proc. Interspeech 2007, 1078-1081, doi: 10.21437/Interspeech.2007-108
@inproceedings{jitsuhiro07_interspeech,
author={Takatoshi Jitsuhiro and Tomoji Toriyama and Kiyoshi Kogure},
title={{Noise suppression using search strategy with multi-model compositions}},
year=2007,
booktitle={Proc. Interspeech 2007},
pages={1078--1081},
doi={10.21437/Interspeech.2007-108}
}