| Paper: | SAM-P6.3 | ||
| Session: | Applications of Multichannel Signal Processing | ||
| Time: | Friday, May 19, 16:30 - 18:30 | ||
| Presentation: | Poster | ||
| Topic: | Sensor Array and Multichannel Signal Processing: Signal detection and estimation | ||
| Title: | MULTICHANNEL SPEECH ENHANCEMENT BASED ON SPEECH SPECTRAL MAGNITUDE ESTIMATION USING GENERALIZED GAMMA PRIOR DISTRIBUTION | ||
| Authors: | Tran Huy Dat, Kazuya Takeda, Nagoya University, Japan; Fumitada Itakura, Meijo University, Japan | ||
| Abstract: | We present multichannel speech enhancement method based on MAP speech spectral magnitude estimation using a generalized gamma model of speech prior distribution, where the model parameters are adapted from actual noisy speech in a frame-by-frame manner. The utilization of a more general prior distribution with its online estimation is shown to be effective for speech spectral estimation. We tested the proposed algorithm in an in-car speech database and obtained significant improvements on the speech recognition performance, particularly under nonstationary noise conditions such as music, air-conditioner and open window. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012