대한음성학회:학술대회논문집 (Proceedings of the KSPS conference)
- 대한음성학회 1996년도 10월 학술대회지
- /
- Pages.464-467
- /
- 1996
Selective Adaptation of Speaker Characteristics within a Subcluster Neural Network
- Haskey, S.J. (Electronic and Electrical Engineering Department Loughborough University) ;
- Datta, S. (Electronic and Electrical Engineering Department Loughborough University)
- 발행 : 1996.10.01
초록
This paper aims to exploit inter/intra-speaker phoneme sub-class variations as criteria for adaptation in a phoneme recognition system based on a novel neural network architecture. Using a subcluster neural network design based on the One-Class-in-One-Network (OCON) feed forward subnets, similar to those proposed by Kung (2) and Jou (1), joined by a common front-end layer. the idea is to adapt only the neurons within the common front-end layer of the network. Consequently resulting in an adaptation which can be concentrated primarily on the speakers vocal characteristics. Since the adaptation occurs in an area common to all classes, convergence on a single class will improve the recognition of the remaining classes in the network. Results show that adaptation towards a phoneme, in the vowel sub-class, for speakers MDABO and MWBTO Improve the recognition of remaining vowel sub-class phonemes from the same speaker
키워드