ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Probabilistic Bilinear Transformation Space-Based Joint Maximum A Posteriori Adaptation
Cited 3 time in scopus Download 8 time Share share facebook twitter linkedin kakaostory
저자
송화전, 이윤근, 김형순
발행일
201210
출처
ETRI Journal, v.34 no.5, pp.783-786
ISSN
1225-6463
출판사
한국전자통신연구원 (ETRI)
DOI
https://dx.doi.org/10.4218/etrij.12.0212.0054
협약과제
11MS2600, 모바일 플랫폼 기반 대화모델 적용 자연어 음성 인터페이스 기술개발, 이윤근
초록
This letter proposes a more advanced joint maximum a posteriori (MAP) adaptation using a prior model based on a probabilistic scheme utilizing the bilinear transformation (BIT) concept. The proposed method not only has scalable parameters but is also based on a single prior distribution without the heuristic parameters of the previous joint BIT-MAP method. Experiment results, irrespective of the amount of adaptation data, show that the proposed method leads to a consistent improvement over the previous method. © 2012 ETRI.
키워드
Bilinear model, MAP, Speaker adaptation
KSP 제안 키워드
Bilinear transformation, Experiment results, Probabilistic scheme, Space based, bilinear model, maximum a posteriori, model-based, prior distribution, prior model, speaker adaptation