Grant Title
Dr. Dolittle Project: A Framework for Classification and Understanding of Animal Vocalizations
Document Type
Conference Proceeding
Publication Date
3-2008
Source Publication
IEEE International Conference on Acoustics, Speech and Signal Processing, 2008: ICASSP; Las Vegas, NV, March 31, 2008 - April 4, 2008
Source ISSN
1520-6149, 978-1-4244-1484-0, 978-1-4244-1483-3
Abstract
In this paper, we propose an MMSE a priori SNR estimator for speech enhancement. This estimator has similar benefits to the well-known decision-directed approach, but does not require an ad-hoc weighting factor to balance the past a priori SNR and current ML SNR estimate with smoothing across frames. Performance is evaluated in terms of estimation error and segmental SNR using the standard logSTSA speech enhancement method. Experimental results show that, in contrast with the decision-directed estimator and ML estimator, the proposed SNR estimator can help enhancement algorithms preserve more weak speech information and efficiently suppress musical noise.
Recommended Citation
Ren, Yao and Johnson, Michael T., "An Improved SNR Estimator for Speech Enhancement" (2008). Dr. Dolittle Project: A Framework for Classification and Understanding of Animal Vocalizations. 18.
https://epublications.marquette.edu/data_drdolittle/18
Document Rights and Citation of Original
Accepted version. Published as a part of the proceedings of the conference, IEEE International Conference on Acoustics, Speech and Signal Processing, 2008: ICASSP; Las Vegas, NV, March 31, 2008 - April 4, 2008, 4901 - 4904. DOI.© 2008 Institute of Electrical and Electronics Engineers (IEEE). Used with permission.