Study of a voice activity detector and its influence on a noise reduction system
Speech Communication
Acoustical and Environmental Robustness in Automatic Speech Recognition
Acoustical and Environmental Robustness in Automatic Speech Recognition
IEICE - Transactions on Information and Systems
Construction and Evaluation of a Large In-Car Speech Corpus
IEICE - Transactions on Information and Systems
Gamma Modeling of Speech Power and Its On-Line Estimation for Statistical Speech Enhancement
IEICE - Transactions on Information and Systems
Model-Based Feature Compensation for Robust Speech Recognition
Fundamenta Informaticae
Multichannel direction-independent speech enhancement using spectral amplitude estimation
EURASIP Journal on Applied Signal Processing
Robust speech recognition using factorial HMMs for home environments
EURASIP Journal on Applied Signal Processing
The long-term adoption of speech recognition in medical applications
CBMS'03 Proceedings of the 16th IEEE conference on Computer-based medical systems
Hi-index | 0.00 |
We present a 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 adaptive estimation is shown to be effective for speech spectral estimation in noisy environments. Furthermore, the multi-channel information in terms of cross-channel statistics are shown to be useful to better adapt the prior distribution parameters to the actual observation, resulting in better performance of speech enhancement algorithm. We tested the proposed algorithm in an in-car speech database and obtained significant improvements of the speech recognition performance, particularly under non-stationary noise conditions such as music, air-conditioner and open window.