An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing

In this paper, a new approach is proposed to improve a sigmoid and conditional smoothing-based speech presence probability (SPP) method for noise power spectral density (PSD) estimation. In this approach, the a posteriori speech absence probability (SAP) is adapted with a sigmoid function mapped to...

Full description

Bibliographic Details
Main Authors: Yong, Pei Chee, Nordholm, Sven
Format: Conference Paper
Published: 2016
Online Access:http://hdl.handle.net/20.500.11937/50628
_version_ 1848758508792578048
author Yong, Pei Chee
Nordholm, Sven
author_facet Yong, Pei Chee
Nordholm, Sven
author_sort Yong, Pei Chee
building Curtin Institutional Repository
collection Online Access
description In this paper, a new approach is proposed to improve a sigmoid and conditional smoothing-based speech presence probability (SPP) method for noise power spectral density (PSD) estimation. In this approach, the a posteriori speech absence probability (SAP) is adapted with a sigmoid function mapped to the normalised spectral average variance in the consecutive frames that can effectively characterise noise variation. The adaptation is also employed in the conditional smoothing stage to characterise the a posteriori SPP, which is then utilised in the noise PSD estimation. Comparison with state of the art methods validates the effectiveness of the proposed method.
first_indexed 2025-11-14T09:45:07Z
format Conference Paper
id curtin-20.500.11937-50628
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:45:07Z
publishDate 2016
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-506282017-09-13T15:37:02Z An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing Yong, Pei Chee Nordholm, Sven In this paper, a new approach is proposed to improve a sigmoid and conditional smoothing-based speech presence probability (SPP) method for noise power spectral density (PSD) estimation. In this approach, the a posteriori speech absence probability (SAP) is adapted with a sigmoid function mapped to the normalised spectral average variance in the consecutive frames that can effectively characterise noise variation. The adaptation is also employed in the conditional smoothing stage to characterise the a posteriori SPP, which is then utilised in the noise PSD estimation. Comparison with state of the art methods validates the effectiveness of the proposed method. 2016 Conference Paper http://hdl.handle.net/20.500.11937/50628 10.1109/IWAENC.2016.7602916 restricted
spellingShingle Yong, Pei Chee
Nordholm, Sven
An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
title An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
title_full An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
title_fullStr An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
title_full_unstemmed An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
title_short An improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
title_sort improved soft decision based noise power estimation employing adaptive prior and conditional smoothing
url http://hdl.handle.net/20.500.11937/50628