Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics

In this paper, a modified a priori SNR estimator is proposed for speech enhancement. The well-known decision-directed (DD) approach is modified by matching each gain function with the noisy speech spectrum at current frame rather than the previous one. The proposed algorithm eliminates the speech tr...

Full description

Bibliographic Details
Main Authors: Yong, Pei, Nordholm, Sven, Dam, Hai Huyen Heidi
Other Authors: Akihiko Sugiyama
Format: Conference Paper
Published: The Institute of Electrical and Electronics Engineers Signal Processing Society 2012
Online Access:http://hdl.handle.net/20.500.11937/32699
_version_ 1848753735927332864
author Yong, Pei
Nordholm, Sven
Dam, Hai Huyen Heidi
author2 Akihiko Sugiyama
author_facet Akihiko Sugiyama
Yong, Pei
Nordholm, Sven
Dam, Hai Huyen Heidi
author_sort Yong, Pei
building Curtin Institutional Repository
collection Online Access
description In this paper, a modified a priori SNR estimator is proposed for speech enhancement. The well-known decision-directed (DD) approach is modified by matching each gain function with the noisy speech spectrum at current frame rather than the previous one. The proposed algorithm eliminates the speech transient distortion and reduces the impact from the choice of the gain function towards the level of smoothing in the SNR estimate. An objective evaluation metric is employed to measure the trade-off between musical noise, noise reduction and speech distortion. Performance is evaluated and compared between a modified sigmoid gain function, the state-of-the-art log-spectral amplitude estimator and the Wiener filter. Simulation results show that the modified DD approach performs better in terms of the trade-off evaluation.
first_indexed 2025-11-14T08:29:15Z
format Conference Paper
id curtin-20.500.11937-32699
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T08:29:15Z
publishDate 2012
publisher The Institute of Electrical and Electronics Engineers Signal Processing Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-326992023-02-07T08:01:19Z Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics Yong, Pei Nordholm, Sven Dam, Hai Huyen Heidi Akihiko Sugiyama Hitoshi Kiya In this paper, a modified a priori SNR estimator is proposed for speech enhancement. The well-known decision-directed (DD) approach is modified by matching each gain function with the noisy speech spectrum at current frame rather than the previous one. The proposed algorithm eliminates the speech transient distortion and reduces the impact from the choice of the gain function towards the level of smoothing in the SNR estimate. An objective evaluation metric is employed to measure the trade-off between musical noise, noise reduction and speech distortion. Performance is evaluated and compared between a modified sigmoid gain function, the state-of-the-art log-spectral amplitude estimator and the Wiener filter. Simulation results show that the modified DD approach performs better in terms of the trade-off evaluation. 2012 Conference Paper http://hdl.handle.net/20.500.11937/32699 10.1109/ICASSP.2012.6288957 The Institute of Electrical and Electronics Engineers Signal Processing Society restricted
spellingShingle Yong, Pei
Nordholm, Sven
Dam, Hai Huyen Heidi
Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics
title Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics
title_full Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics
title_fullStr Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics
title_full_unstemmed Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics
title_short Trade-off evaluation for speech enhancement algorithms with respect to the a priori SNR estimation acoustics
title_sort trade-off evaluation for speech enhancement algorithms with respect to the a priori snr estimation acoustics
url http://hdl.handle.net/20.500.11937/32699