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...
| Main Authors: | , |
|---|---|
| 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 |