梁衍学 (Yanxue Liang) - マイポータル - researchmap

基本情報

学位: 修士(上海交通大学)

J-GLOBAL ID: 200901079554367430
researchmap会員ID: 5000093746

研究キーワード

6

the result is arbitrary filtered version of sources which dramatically decrease the performance of ASR. How to eliminate the artificial filtering effect while separating sources is my research task.
it is difficult to get pure speech signal when interference or reflection exist. BSS is a technique to recover the sources from mixtures without any prior information. When applied BSS to speech case
Pure speech signal is important for Automatic Speech Recognition (ASR) system. But in daily life
the result is arbitrary filtered version of sources which dramatically decrease the performance of ASR. How to eliminate the artificial filtering effect while separating sources is my research task.
it is difficult to get pure speech signal when interference or reflection exist. BSS is a technique to recover the sources from mixtures without any prior information. When applied BSS to speech case
Pure speech signal is important for Automatic Speech Recognition (ASR) system. But in daily life

経歴

1

東京工業大学理工学研究科機械物理工学専攻理工学研究科(博士課程）機械物理工学専攻, 大学院学生（博士課程）

所属学協会

2

共同研究・競争的資金等の研究課題

2

Blind Source Separation based speech enhancenment

2004年 - 2007年
Blind Source Separation based speech enhancenment

2004年 - 2007年