Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
| Paper: | SP-P1.7 |
| Session: | Speech Coding for Networks / Single-Channel Speech Enhancement |
| Time: | Tuesday, May 18, 13:00 - 15:00 |
| Presentation: |
Poster |
| Topic: |
Speech Processing: Speech Enhancement |
| Title: |
A TWO-STEP NOISE REDUCTION TECHNIQUE |
| Authors: |
Cyril Plapous; France Télécom R&D - DIH/IPS | | |
| | Claude Marro; France Télécom R&D - DIH/IPS | | |
| | Laurent Mauuary; France Télécom R&D - DIH/IPS | | |
| | Pascal Scalart; ENSSAT - LASTI | | |
| Abstract: |
This paper adresses the problem of single microphone speech enhancement in noisy environments. Common short-time noise reduction techniques proposed in the art are expressed as a spectral gain depending on the a priori SNR. In the well-known decision-directed approach, the a priori SNR depends on the previous frame speech spectrum estimation. As a consequence the gain function matches the previous frame rather than the current one which degrades the noise reduction performance. We propose a new method called Two-Step Noise Reduction (TSNR) technique which solves this problem while maintaining the benefits of the decision-directed approach. This method is analysed and results in voice communication and speech recognition context are given. |
| |
| Back | |