Conference proceeding
Log spectra enhancement using speaker dependent priors for speaker verification
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4540-4543
May 2011
Abstract
We present a variational Bayesian algorithm that enhances the log spectra of noisy speech using speaker dependent priors. This algorithm extends prior work by Frey et al. where the Algonquin algorithm was introduced to enhance speech log spectra in order to improve speech recognition in noisy environments. Our work is built on the intuition that speaker dependent priors would work better than priors that attempt to capture global speech properties. Experimental results using the TIMIT data set and the NIST 2004 speaker recognition evaluation (SRE) data are presented to demonstrate the algorithm's performance.
Metrics
10 Record Views
Details
- Title
- Log spectra enhancement using speaker dependent priors for speaker verification
- Creators
- Ciira wa Maina - Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USAJohn MacLaren Walsh - Drexel UniversityIEEE
- Publication Details
- 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 4540-4543
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000296062405037
- Scopus ID
- 2-s2.0-80051643204
- Other Identifier
- 991019170579704721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Acoustics
- Engineering, Electrical & Electronic
- Imaging Science & Photographic Technology