Compressive speech enhancement
This paper presents an alternative approach to speech enhancement by using compressed sensing (CS). CS is a new sampling theory, which states that sparse signals can be reconstructed from far fewer measurements than the Nyquist sampling. As such, CS can be exploited to reconstruct only the sparse co...
| Main Authors: | , , |
|---|---|
| Format: | Journal Article |
| Published: |
Elsevier
2013
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/35000 |
| _version_ | 1848754376930230272 |
|---|---|
| author | Low, S. Pham, DucSon Venkatesh, S. |
| author_facet | Low, S. Pham, DucSon Venkatesh, S. |
| author_sort | Low, S. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This paper presents an alternative approach to speech enhancement by using compressed sensing (CS). CS is a new sampling theory, which states that sparse signals can be reconstructed from far fewer measurements than the Nyquist sampling. As such, CS can be exploited to reconstruct only the sparse components (e.g., speech) from the mixture of sparse and non-sparse components (e.g., noise). This is possible because in a time-frequency representation, speech signal is sparse whilst most noise is non-sparse. Derivation shows that on average the signal to noise ratio (SNR) in the compressed domain is greater or equal than the uncompressed domain. Experimental results concur with the derivation and the proposed CS scheme achieves better or similar perceptual evaluation of speech quality (PESQ) scores and segmental SNR compared to other conventional methods in a wide range of input SNR. |
| first_indexed | 2025-11-14T08:39:26Z |
| format | Journal Article |
| id | curtin-20.500.11937-35000 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:39:26Z |
| publishDate | 2013 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-350002017-09-13T15:41:23Z Compressive speech enhancement Low, S. Pham, DucSon Venkatesh, S. Speech enhancement Sparsity Compressed sensing This paper presents an alternative approach to speech enhancement by using compressed sensing (CS). CS is a new sampling theory, which states that sparse signals can be reconstructed from far fewer measurements than the Nyquist sampling. As such, CS can be exploited to reconstruct only the sparse components (e.g., speech) from the mixture of sparse and non-sparse components (e.g., noise). This is possible because in a time-frequency representation, speech signal is sparse whilst most noise is non-sparse. Derivation shows that on average the signal to noise ratio (SNR) in the compressed domain is greater or equal than the uncompressed domain. Experimental results concur with the derivation and the proposed CS scheme achieves better or similar perceptual evaluation of speech quality (PESQ) scores and segmental SNR compared to other conventional methods in a wide range of input SNR. 2013 Journal Article http://hdl.handle.net/20.500.11937/35000 10.1016/j.specom.2013.03.003 Elsevier restricted |
| spellingShingle | Speech enhancement Sparsity Compressed sensing Low, S. Pham, DucSon Venkatesh, S. Compressive speech enhancement |
| title | Compressive speech enhancement |
| title_full | Compressive speech enhancement |
| title_fullStr | Compressive speech enhancement |
| title_full_unstemmed | Compressive speech enhancement |
| title_short | Compressive speech enhancement |
| title_sort | compressive speech enhancement |
| topic | Speech enhancement Sparsity Compressed sensing |
| url | http://hdl.handle.net/20.500.11937/35000 |