Proceedings of the Korean Society of Broadcast Engineers Conference (한국방송∙미디어공학회:학술대회논문집)
- 2011.07a
- /
- Pages.85-88
- /
- 2011
A Single Channel Speech Enhancement for Automatic Speech Recognition
- Lee, Jinkyu (Dept. of Electrical and Electronic Engineering, Yonsei University) ;
- Seo, Hyunson (Dept. of Electrical and Electronic Engineering, Yonsei University) ;
- Kang, Hong-Goo (Dept. of Electrical and Electronic Engineering, Yonsei University)
- Published : 2011.07.07
Abstract
This paper describes a single channel speech enhancement as the pre-processor of automatic speech recognition system. The improvements are based on using optimally modified log-spectra (OM-LSA) gain function with a non-causal a priori signal-to-noise ratio (SNR) estimation. Experimental results show that the proposed method gives better perceptual evaluation of speech quality score (PESQ) and lower log-spectral distance, and also better word accuracy. In the enhancement system, parameters was turned for automatic speech recognition.
Keywords