상세정보
학술지
A New Distance Measure for a Variable-Sized Acoustic Model Based on MDL Technique
- 발행일
- 201010
- 출처
- ETRI Journal, v.32 no.5, pp.795-800
- ISSN
- 1225-6463
- 출판사
- 한국전자통신연구원 (ETRI)
- 협약과제
- 09MS4200, 휴대형 한/영 자동통역 기술개발, 김상훈
- 초록
- Embedding a large vocabulary speech recognition system in mobile devices requires a reduced acoustic model obtained by eliminating redundant model parameters. In conventional optimization methods based on the minimum description length (MDL) criterion, a binary Gaussian tree is built at each state of a hidden Markov model by iteratively finding and merging similar mixture components. An optimal subset of the tree nodes is then selected to generate a downsized acoustic model. To obtain a better binary Gaussian tree by improving the process of finding the most similar Gaussian components, this paper proposes a new distance measure that exploits the difference in likelihood values for cases before and after two components are combined. The mixture weight of Gaussian components is also introduced in the component merging step. Experimental results show that the proposed method outperforms MDL-based optimization using either a Kullback-Leibler (KL) divergence or weighted KL divergence measure. The proposed method could also reduce the acoustic model size by 50% with less than a 1.5% increase in error rate compared to a baseline system. © 2010 ETRI.
- KSP 제안 키워드
- Baseline system, Divergence measure, Kullback-Leibler (KL) divergence, Minimum description length (MDL) criterion, Mobile devices, Model parameter, Speech recognition system, acoustic model, distance measure, error rate, hidden Markov Model