Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SS-6.3 |
| Session: | Convolutive Blind Source Separation for Speech and Audio Signals |
| Time: | Wednesday, May 19, 16:10 - 16:30 |
| Presentation: |
Special Session Lecture |
| Topic: |
Special Sessions: Convolutive Blind Source Separation for Speech and Audio Signals |
| Title: |
CONVOLUTIVE BLIND SOURCE SEPARATION FOR MORE THAN TWO SOURCES IN THE FREQUENCY DOMAIN |
| Authors: |
Hiroshi Sawada; NTT Corporation | | |
| | Ryo Mukai; NTT Corporation | | |
| | Shoko Araki; NTT Corporation | | |
| | Shoji Makino; NTT Corporation | | |
| Abstract: |
Blind source separation (BSS) for convolutive mixtures can be efficiently achieved in the frequency domain, where independent component analysis is performed separately in each frequency bin. However, frequency-domain BSS involves a permutation problem, which is well known as a difficult problem, especially when the number of sources is large. This paper presents a method for solving the permutation problem, which works well even for many sources. The successful solution for the permutation problem highlights another problem with frequency-domain BSS that arises from the circularity of discrete frequency representation. This paper discusses the phenomena of the problem and presents a method for solving it. With these two methods, we can separate many sources with a practical execution time. Moreover, real-time processing is currently possible for up to three sources with our implementation. |
| |
| Back | |