2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
AUD-2: Audio and Speech Source Separation 2: Music and Singing Voice Separation |
| Session Type: Poster |
| Time: Tuesday, 8 June, 13:00 - 13:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Yu Wang, New York University |
| AUD-2.1: SEMI-SUPERVISED SINGING VOICE SEPARATION WITH NOISY SELF-TRAINING |
| Zhepei Wang; University of Illinois at Urbana-Champaign |
| Ritwik Giri; Amazon Web Services |
| Umut Isik; Amazon Web Services |
| Jean-Marc Valin; Amazon Web Services |
| Arvindh Krishnaswamy; Amazon Web Services |
| AUD-2.2: NEURO-STEERED MUSIC SOURCE SEPARATION WITH EEG-BASED AUDITORY ATTENTION DECODING AND CONTRASTIVE-NMF |
| Giorgia Cantisani; LTCI, Télécom Paris, Institut Polytechnique de Paris |
| Slim Essid; LTCI, Télécom Paris, Institut Polytechnique de Paris |
| Gaël Richard; LTCI, Télécom Paris, Institut Polytechnique de Paris |
| AUD-2.3: COMPLEX RATIO MASKING FOR SINGING VOICE SEPARATION |
| Yixuan Zhang; The Ohio State University |
| Yuzhou Liu; The Ohio State University |
| DeLiang Wang; The Ohio State University |
| AUD-2.4: TRANSCRIPTION IS ALL YOU NEED: LEARNING TO SEPARATE MUSICAL MIXTURES WITH SCORE AS SUPERVISION |
| Yun-Ning Hung; Georgia Institute of Technology |
| Gordon Wichern; Mitsubishi Electric Research Laboratories (MERL) |
| Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL) |
| AUD-2.5: ALL FOR ONE AND ONE FOR ALL: IMPROVING MUSIC SEPARATION BY BRIDGING NETWORKS |
| Ryosuke Sawata; Sony Corporation |
| Stefan Uhlich; Sony Corporation |
| Shusuke Takahashi; Sony Corporation |
| Yuki Mitsufuji; Sony Corporation |
| AUD-2.6: AN HRNET-BLSTM MODEL WITH TWO-STAGE TRAINING FOR SINGING MELODY EXTRACTION |
| Yongwei Gao; Fudan University |
| Xingjian Du; ByteDance AI Lab |
| Bilei Zhu; ByteDance AI Lab |
| Xiaoheng Sun; Fudan University |
| Wei Li; Fudan University |
| Zejun Ma; ByteDance AI Lab |