Title :
Noise compensation for speech recognition with arbitrary additive noise
Author_Institution :
Sch. of Comput. Sci., Queen´´s Univ. Belfast, UK
Abstract :
A method for noise compensation for additive background noise based only on clean speech training data is described, assuming arbitrary noise characteristics. Experiments on Aurora 2 indicate that the new method has achieved a performance comparable to, or better than, the performance obtained by the baseline model trained on multi-condition data.
Keywords :
AWGN; probability; speech recognition; Aurora 2; additive background noise; arbitrary additive noise; arbitrary noise characteristics; baseline model; multicondition data; noise compensation; probability; speech recognition; speech training data;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:20040113
