Abstract
Speech understanding in adverse acoustic environments is still a major problem for users of hearinginstruments. Recent studies on supervised speech segregation show good promise to alleviate this problem by separating speech-dominated from noise-dominated spectro-temporal regions with estimated time-frequency masks. The current study compared a previously proposed feature set to a novel auditorymodel based feature set using a common deep neural network based speech enhancement framework. The performance of both feature extraction methods was evaluated with objective measurements and a subjective listening test to measure speech perception scores in terms of intelligibility and quality with 17 hearing-impaired listeners. Significant improvements in speech intelligibility and quality ratings were found for both feature extraction systems. However, the auditory-model based feature set showed superior performance compared to the comparison feature set indicating that auditory-model based processing could provide further improvements for supervised speech segregation systems and their potential applications in hearing instruments.
Original language | English |
---|---|
Title of host publication | 2016 24th European Signal Processing Conference, EUSIPCO 2016 |
Subtitle of host publication | proceedings |
Place of Publication | Budapest, Hungary |
Publisher | European Signal Processing Conference, EUSIPCO |
Pages | 2300-2304 |
Number of pages | 5 |
ISBN (Electronic) | 9780992862657 |
DOIs | |
Publication status | Published - 28 Nov 2016 |
Externally published | Yes |
Event | 24th European Signal Processing Conference, EUSIPCO 2016 - Budapest, Hungary Duration: 28 Aug 2016 → 2 Sept 2016 |
Other
Other | 24th European Signal Processing Conference, EUSIPCO 2016 |
---|---|
Country/Territory | Hungary |
City | Budapest |
Period | 28/08/16 → 2/09/16 |
Keywords
- Auditory models
- Deep neural networks
- Hearing aids
- Speech enhancement