본문 바로가기

Speaker adaptation using probabilistic linear discriminant analysis for continuous speech recognition

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q3Scopus Q2
저널
ELECTRONICS LETTERS49(25) · 2013
피인용
Web of Science 2
JCR IF
JCR 2012 1.038
ISSN
0013-5194

저자

  1. 정용원제1저자School of Electrical Engineering, Pusan National University, South Korea

초록

The application of probabilistic linear discriminant analysis (PLDA) to speaker adaptation for automatic speech recognition based on hidden Markov models is proposed. By expressing the set of acoustic models of each of the training speakers in a matrix and treating each column as a sample, the small sample problem that can be encountered in PLDA if only one sample is available for each training speaker is overcome. In the continuous speech recognition experiments, the performance of the PLDA based approach improves over the principal component analysis (PC) based approach and the two-dimensional PCA based approach for adaptation data longer than 12 s.

키워드

HIDDEN MARKOV-MODELSMAXIMUM-LIKELIHOOD

식별자

WoS UID
000327714500037