BROWSE
Detail
Conference Paper
SNR-Based Mask Compensation for Computational Auditory Scene Analysis Applied to Speech Recognition in a Car Environment
Cited - time in 
Share 
Share
- Authors
- Ji Hun Park, Seon Man Kim, Jae Sam Yoon, Hong Kook Kim, Sung Joo Lee, Yun keun Lee
- Issue Date
- 2010-09
- Citation
- International Speech Communication Association (INTERSPEECH) 2010, pp.725-728
- Publisher
- ISCA
- Language
- English
- Type
- Conference Paper
- Abstract
- In this paper, we propose a computational auditory scene analysis (CASA)-based front-end for two-microphone speech recognition in a car environment. One of the important issues associated with CASA is the accurate estimation of mask information for target speech separation within multiple microphone noisy speech. For such a task, the time-frequency mask information is compensated through the signal-to-noise ratio resulted from a beamformer to adjust the noise quantity included in noisy speech. We evaluate the performance of an automatic speech recognition (ASR) system employing a CASA-based front-end with the proposed mask compensation method. In addition, we compare its performance with those employing a CASA-based front-end without mask compensation and the beamforming-based front-end. As a result, the CASA-based front-end achieves an average word error rate (WER) reduction of 8.57% when the proposed mask compensation method is applied. In addition, the CASA-based front-end with the proposed method provides a relative WER reduction of 26.52%, compared with the beamforming-based front-end.
- KSP Keywords
- Compensation method, Computational auditory scene analysis, Front-End, Signal noise ratio(SNR), Signal-to-Noise, Speech Separation, accurate estimation, automatic speech recognition(ASR), noisy speech, time frequency(T-F), time-frequency mask