BROWSE
Detail
Journal Article
Adaptive Channel Normalization Based on Infomax Algorithm for Robust Speech Recognition
- Authors
- Ho-Young Jung
- Issue Date
- 2007-06
- Citation
- ETRI Journal, v.29 no.3, pp.300-304
- ISSN
- 1225-6463
- Publisher
- 한국전자통신연구원 (ETRI)
- Language
- English
- Type
- Journal Article
- Project Code
- 06MW1800, Development of large vocabulary/interactive distributed VUI for new growth engine industries, Young Jik Lee
- Abstract
- This paper proposes a new data-driven method for high-pass approaches, which suppresses slow-varying noise components. Conventional high-pass approaches are based on the idea of decorrelating the feature vector sequence, and are trying for adaptability to various conditions. The proposed method is based on temporal local decorrelation using the information-maximization theory for each utterance. This is performed on an utterance-by-utterance basis, which provides an adaptive channel normalization filter for each condition. The performance of the proposed method is evaluated by isolated-word recognition experiments with channel distortion. Experimental results show that the proposed method yields outstanding improvement for channel-distorted speech recognition.
- KSP Keywords
- Feature Vector, Infomax algorithm, Isolated Word Recognition, Noise components, Slow-varying, Various conditions, channel normalization, data-driven method, high pass, robust speech recognition