A novel associative memory approach to speech enhancement in a vehicular environment
Numerous attempts have been undertaken to apply the spectral subtraction method to cancel noise perturbations but these efforts have yet to produce an algorithm that is able to adapt well to the environmental changes in the perturbations. In addition, the variants of the spectral subtraction method...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier Limited
2009
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/9582/ http://irep.iium.edu.my/9582/1/A_novel_associative_memory_approach_to_speech_enhancement.pdf |
| _version_ | 1848777139023773696 |
|---|---|
| author | Abdul Rahman, Abdul Wahab Quek, Chai |
| author_facet | Abdul Rahman, Abdul Wahab Quek, Chai |
| author_sort | Abdul Rahman, Abdul Wahab |
| building | IIUM Repository |
| collection | Online Access |
| description | Numerous attempts have been undertaken to apply the spectral subtraction method to cancel noise perturbations but these efforts have yet to produce an algorithm that is able to adapt well to the environmental changes in the perturbations. In addition, the variants of the spectral subtraction method so far proposed in the literature would require a non-voice activity detector (NVAD), for a single microphone system, to store the perturbation. This is used as an estimate for the reference signal. Inaccuracy in the perturbation estimates causes the cleaned speech to be corrupted by musical artifacts, which is unacceptable. Post processing of signals corrupted by the musical artifacts is very costly. This paper provides an alternative approach that employs associative memory for speech enhancement. Extensive comparison is made using the soft computing approaches for noise cancellation based on associative memories. A set of stereo microphones captures the corrupted speech in a vehicle and is used to point to the closest associative memory location. The Wiener filter approach is used to cancel the noise. The paper discusses novel examples of the associative memories using the cerebellum model for noise modeling. Experimental results show the potential of these novel soft computing architectures in generating and adapting the required Weiner filters to cancel perturbation even at signal to noise ratio (SNR) of less than -13 dB. |
| first_indexed | 2025-11-14T14:41:14Z |
| format | Article |
| id | iium-9582 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T14:41:14Z |
| publishDate | 2009 |
| publisher | Elsevier Limited |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-95822013-09-14T14:42:09Z http://irep.iium.edu.my/9582/ A novel associative memory approach to speech enhancement in a vehicular environment Abdul Rahman, Abdul Wahab Quek, Chai QA75 Electronic computers. Computer science T58.5 Information technology Numerous attempts have been undertaken to apply the spectral subtraction method to cancel noise perturbations but these efforts have yet to produce an algorithm that is able to adapt well to the environmental changes in the perturbations. In addition, the variants of the spectral subtraction method so far proposed in the literature would require a non-voice activity detector (NVAD), for a single microphone system, to store the perturbation. This is used as an estimate for the reference signal. Inaccuracy in the perturbation estimates causes the cleaned speech to be corrupted by musical artifacts, which is unacceptable. Post processing of signals corrupted by the musical artifacts is very costly. This paper provides an alternative approach that employs associative memory for speech enhancement. Extensive comparison is made using the soft computing approaches for noise cancellation based on associative memories. A set of stereo microphones captures the corrupted speech in a vehicle and is used to point to the closest associative memory location. The Wiener filter approach is used to cancel the noise. The paper discusses novel examples of the associative memories using the cerebellum model for noise modeling. Experimental results show the potential of these novel soft computing architectures in generating and adapting the required Weiner filters to cancel perturbation even at signal to noise ratio (SNR) of less than -13 dB. Elsevier Limited 2009-12 Article PeerReviewed application/pdf en http://irep.iium.edu.my/9582/1/A_novel_associative_memory_approach_to_speech_enhancement.pdf Abdul Rahman, Abdul Wahab and Quek, Chai (2009) A novel associative memory approach to speech enhancement in a vehicular environment. Expert System with Application, 36 (10). pp. 12120-12130. ISSN 09574174 10.1016/j.eswa.2009.03.071 |
| spellingShingle | QA75 Electronic computers. Computer science T58.5 Information technology Abdul Rahman, Abdul Wahab Quek, Chai A novel associative memory approach to speech enhancement in a vehicular environment |
| title | A novel associative memory approach to speech enhancement
in a vehicular environment |
| title_full | A novel associative memory approach to speech enhancement
in a vehicular environment |
| title_fullStr | A novel associative memory approach to speech enhancement
in a vehicular environment |
| title_full_unstemmed | A novel associative memory approach to speech enhancement
in a vehicular environment |
| title_short | A novel associative memory approach to speech enhancement
in a vehicular environment |
| title_sort | novel associative memory approach to speech enhancement
in a vehicular environment |
| topic | QA75 Electronic computers. Computer science T58.5 Information technology |
| url | http://irep.iium.edu.my/9582/ http://irep.iium.edu.my/9582/ http://irep.iium.edu.my/9582/1/A_novel_associative_memory_approach_to_speech_enhancement.pdf |