Conference proceeding
Joint speech enhancement and speaker identification using approximate Bayesian inference
2010 44th Annual Conference on Information Sciences and Systems, pp 1-6
Mar 2010
Abstract
A variational Bayesian principle is applied to derive a iterative technique for jointly identifying a speaker in a noisy acoustic environment and enhancing their speech. Intuitively, it is clear that employing speaker dependent priors for speech allows for better speech enhancement, while cleaner speech allows for better speaker identification. The derived algorithm reflects this intuition by iteratively exchanging information between the enhancement and identification tasks. Experimental results using the TIMIT data set are presented to demonstrate the algorithm's performance.
Metrics
1 Record Views
Details
- Title
- Joint speech enhancement and speaker identification using approximate Bayesian inference
- Creators
- Ciira wa MainaJohn MacLaren Walsh
- Publication Details
- 2010 44th Annual Conference on Information Sciences and Systems, pp 1-6
- Publisher
- IEEE
- Number of pages
- 6
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Scopus ID
- 2-s2.0-77953727617
- Other Identifier
- 991022096382904721