BROWSE
Detail
Conference Paper
Discriminative Noise Adaptive Training Approach for an Environment Migration
Cited - time in 
Share 
Share
- Authors
- Byung-Ok Kang, Ho-Young Jung, Yun-Keun Lee
- Issue Date
- 2007-08
- Citation
- International Speech Communication Association (INTERSPEECH) 2007, pp.2085-2088
- Publisher
- ISCA
- Language
- English
- Type
- Conference Paper
- Abstract
- A combined strategy of noise-adaptive training (NAT) and discriminative-based adaptation is proposed for effective migration of speech recognition systems to other noisy environments. NAT is an effective approach for real-field applications, but does not satisfy the minimum classification error (MCE) criterion for the recognition process and adapts poorly to new environments. The proposed method makes up for the weak points in discriminative adaptation strategies, and presents a new method for improving the MCE approach. Using this new method, experimental results show that the speech recognition system can successfully be migrated to other environments using specific-condition data of the target environment.
- KSP Keywords
- Field application, Speech recognition system, adaptation strategies, minimum classification error, new method, noise adaptive training, noisy environments, target environment, weak points