Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-L10.4 |
| Session: | Multichannel Speech Enhancement |
| Time: | Friday, May 21, 14:00 - 14:20 |
| Presentation: |
Lecture |
| Topic: |
Speech Processing: Speech Enhancement |
| Title: |
SPEECH ENHANCEMENT BASED ON A COMBINED MULTI-CHANNEL ARRAY WITH CONSTRAINED INTERATIVE AND AUDITORY MASKED PROCESSING |
| Authors: |
John H. L. Hansen; University of Colorado, Boulder | | |
| | Xianxian Zhang; University of Colorado, Boulder | | |
| | Kathryn Arehart; University of Colorado, Boulder | | |
| Abstract: |
While a number of studies have investigated various speech enhancement and noise suppression schemes, most consider either a single channel or array processing framework. Clearly there are potential advantages in leveraging the strengths of array processing solutions in suppressing noise from a direction other than the speaker, with that seen in single channel methods that include speech spectral constraints or psychoacoustically motivated processing. In this paper, we propose to integrate a combined fixed/adaptive beamforming algorithm (CFA-BF) for speech enhancement with two single channel methods based on speech spectral constrained iterative processing (Auto-LSP), and an auditory masked threshold based method using equivalent rectangular bandwidth filtering (GMMSE-AMT-ERB). After formulating the method, we evaluate performance on a subset of the TIMIT corpus with four real noise sources. We demonstrate a consistent level of noise suppression and voice communication quality improvement using the proposed method as reflected by an overall average 26dB increase in SegSNR from the original degraded audio corpus. |
| |
| Back | |