音声認識のための高速環境適応

概要

論文の詳細を見る
This paper proposes a rapid environment adaptation algorithm based on spectrum equalization (REALISE). In practical speech recognition applications, differences between training and testing environments often seriously diminish recognition accuracy. These environmental difference can be classified into two types: difference in additive nosie and differences in multiplicative noise in the spectral domain. The proposed method calculates time-alignment between a testing utterance and the closest reference pattern to it, and then calculates the noise differences between the two according to the time-alignment. Then, we adapt all reference patterns to the testing environment using the differences. Finally, the testing utterance is recognized using the adapted reference patterns. In a 250 Japanese word recognition task, in which the training and testing microphones were of two different types, REALISE improved recognition accuracy from 87% to 96%.
社団法人日本音響学会の論文