SPE-L11: Speech Separation and Extraction I: Single Channel |
| Session Type: Lecture |
| Time: Thursday, 7 May, 09:00 - 11:00 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Tomohiro Nakatani, NTT |
| SPE-L11.1: DEEP CASA FOR TALKER-INDEPENDENT MONAURAL SPEECH SEPARATION |
| Yuzhou Liu; Ohio State University |
| Masood Delfarah; Ohio State University |
| DeLiang Wang; Ohio State University |
| SPE-L11.2: DEMYSTIFYING TASNET: A DISSECTING APPROACH |
| Jens Heitkaemper; Paderborn University |
| Darius Jakobeit; Paderborn University |
| Christoph Boeddeker; Paderborn University |
| Lukas Drude; Paderborn University |
| Reinhold Haeb-Umbach; Paderborn University |
| SPE-L11.3: FILTERBANK DESIGN FOR END-TO-END SPEECH SEPARATION |
| Manuel Pariente; INRIA Nancy |
| Samuele Cornell; Università Politecnica delle Marche |
| Antoine Deleforge; INRIA Nancy |
| Emmanuel Vincent; INRIA Nancy |
| SPE-L11.4: INTERRUPTED AND CASCADED PERMUTATION INVARIANT TRAINING FOR SPEECH SEPARATION |
| Gene-Ping Yang; National Taiwan University |
| Szu-Lin Wu; National Taiwan University |
| Yao-Wen Mao; National Taiwan University |
| Hung-yi Lee; National Taiwan University |
| Lin-shan Lee; National Taiwan University |
| SPE-L11.5: MIXUP-BREAKDOWN: A CONSISTENCY TRAINING METHOD FOR IMPROVING GENERALIZATION OF SPEECH SEPARATION MODELS |
| Max W. Y. Lam; Tencent AI Lab |
| Jun Wang; Tencent AI Lab |
| Dan Su; Tencent AI Lab |
| Dong Yu; Tencent AI Lab |
| SPE-L11.6: AN ONLINE SPEAKER-AWARE SPEECH SEPARATION APPROACH BASED ON TIME-DOMAIN REPRESENTATION |
| Hui Wang; University of Science and Technology of China |
| Yan Song; University of Science and Technology of China |
| Zeng-Xi Li; Microsoft China |
| Ian McLoughlin; School of Computing, University of Kent |
| Li-Rong Dai; University of Science and Technology of China |