S Sato   H Segi   K Onoe   E Miyasaka   H Isono   T Imai   A Ando   
ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE 88(2) 41-51 2005年 [査読有り]
In speech recognition systems where the speaker and utterance environment cannot be designated, the drop in recognition precision due to the incompatibility of the input speech and acoustic model's training data is a problem. Although this problem...
K Onoe   H Segi   T Kobayakawa   S Sato   S Homma   T Imai   A Ando   
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E86D(3) 483-488 2003年3月 [査読有り]
In this paper, we propose a new technique of filter bank subtraction for robust speech recognition under various acoustic conditions. Spectral subtraction is a simple and useful technique for reducing the influence of additive noise. Conventional ...
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E86D(1) 15-25 2003年1月 [査読有り]
There is a strong demand to expand captioned broadcasting for TV news programs in Japan. However, keyboard entry of captioned manuscripts for news program cannot keep pace with the speed of speech, because in the case of Japanese it takes time to ...