MALSORI (대한음성학회지:말소리)
- Issue 65
- /
- Pages.153-168
- /
- 2008
- /
- 1226-1173(pISSN)
Application of Shape Analysis Techniques for Improved CASA-Based Speech Separation
CASA 기반 음성분리 성능 향상을 위한 형태 분석 기술의 응용
- Published : 2008.03.30
Abstract
We propose a new method to apply shape analysis techniques to a computational auditory scene analysis (CASA)-based speech separation system. The conventional CASA-based speech separation system extracts speech signals from a mixture of speech and noise signals. In the proposed method, we complement the missing speech signals by applying the shape analysis techniques such as labelling and distance function. In the speech separation experiment, the proposed method improves signal-to-noise ratio by 6.6 dB. When the proposed method is used as a front-end of speech recognizers, it improves recognition accuracy by 22% for the speech-shaped stationary noise condition and 7.2% for the two-talker noise condition at the target-to-masker ratio than or equal to -3 dB.