Title :
Multi-speaker adaptation for robust speech recognition under ubiquitous environment
Author :
Shih, Po-Yi ; Wang, Jhing-Fa ; Lin, Yuan-Ning ; Fu, Zhong-hua
Author_Institution :
Dept. of Electr. Eng., Nat. Cheng Kung Univ., Tainan, Taiwan
Abstract :
This paper presents a multi-speaker adaptation for robust speech recognition under ubiquitous environment. The goal is to adapt the speech recognition model for each speaker correctly in ubiquitous multi-speaker environment. We integrate speaker recognition and unsupervised speaker adaptation method to promote the speech recognition performances. Specifically we employ a confidence measure to reduce the possible negative adaptation caused by the environment noise or the recognition errors. The experimental results show that the proposed framework can efficiently promote the average recognition accuracy to 80~90% for multi-speaker ubiquitous speech recognition.
Keywords :
speaker recognition; ubiquitous computing; average recognition; confidence measure; environment noise; multispeaker adaptation; multispeaker ubiquitous speech recognition; negative adaptation; recognition error; robust speech recognition; speaker recognition; speech recognition model; speech recognition performance; ubiquitous environment; ubiquitous multispeaker environment; unsupervised speaker adaptation; Kernel; Loudspeakers; Matrix decomposition; Maximum likelihood linear regression; Parameter estimation; Robustness; Speaker recognition; Speech recognition; Support vector machine classification; Support vector machines;
Conference_Titel :
Speech Database and Assessments, 2009 Oriental COCOSDA International Conference on
Conference_Location :
Urumqi
Print_ISBN :
978-1-4244-4400-7
Electronic_ISBN :
978-1-4244-4400-7
DOI :
10.1109/ICSDA.2009.5278364
