| Paper ID | SS-13.3 |
| Paper Title |
CONVOLUTIVE TRANSFER FUNCTION INVARIANT SDR TRAINING CRITERIA FOR MULTI-CHANNEL REVERBERANT SPEECH SEPARATION |
| Authors |
Christoph Boeddeker, Paderborn University, Germany; Wangyou Zhang, Shanghai Jiao Tong University, China; Tomohiro Nakatani, Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Naoyuki Kamo, NTT Corporation, Japan; Yanmin Qian, Shanghai Jiao Tong University, China; Reinhold Haeb-Umbach, Paderborn University, Germany |
| Session | SS-13: Recent Advances in Multichannel and Multimodal Machine Learning for Speech Applications |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation Time: | Thursday, 10 June, 16:30 - 17:15 |
| Presentation |
Poster
|
| Topic |
Special Sessions: Recent Advances in Multichannel and Multimodal Machine Learning for Speech Applications |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Time-domain training criteria have proven to be very effective for the separation of single-channel non-reverberant speech mixtures. Likewise, mask-based beamforming has shown impressive performance in multi-channel reverberant speech enhancement and source separation. Here, we propose to combine neural network supported multi-channel source separation with a time-domain training objective function. For the objective we propose to use a convolutive transfer function invariant Signal-to-Distortion Ratio (CI-SDR) based loss. While this is a well-known evaluation metric (BSS Eval), it has not been used as a training objective before. To show the effectiveness, we demonstrate the performance on LibriSpeech based reverberant mixtures. On this task, the proposed system approaches the error rate obtained on single-source non-reverberant input, i.e., LibriSpeech test_clean, with a difference of only 1.2 percentage points, thus outperforming a conventional permutation invariant training based system and alternative objectives like Scale Invariant Signal-to-Distortion Ratio by a large margin. |
