2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-6: Speech Enhancement 2: Speech Separation and Dereverberation |
| Session Type: Poster |
| Time: Tuesday, 8 June, 14:00 - 14:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Takuya Yoshioka, Microsoft Research |
| SPE-6.1: ONE SHOT LEARNING FOR SPEECH SEPARATION |
| Yuan-Kuei Wu; National Taiwan University |
| Kuan-Po Huang; National Taiwan University |
| Yu Tsao; Academia Sinica |
| Hung-yi Lee; National Taiwan University |
| SPE-6.2: TRAINING NOISY SINGLE-CHANNEL SPEECH SEPARATION WITH NOISY ORACLE SOURCES: A LARGE GAP AND A SMALL STEP |
| Matthew Maciejewski; Johns Hopkins University |
| Jing Shi; Chinese Academy of Sciences |
| Shinji Watanabe; Johns Hopkins University |
| Sanjeev Khudanpur; Johns Hopkins University |
| SPE-6.3: SPEAKER AND DIRECTION INFERRED DUAL-CHANNEL SPEECH SEPARATION |
| Chenxing Li; Institute of Automation, Chinese Academy of Sciences |
| Jiaming Xu; Institute of Automation, Chinese Academy of Sciences |
| Nima Mesgarani; Columbia University |
| Bo Xu; Institute of Automation, Chinese Academy of Sciences |
| SPE-6.4: SPEECH DEREVERBERATION USING VARIATIONAL AUTOENCODERS |
| Deepak Baby; Amazon Alexa |
| Hervé Bourlard; Idiap Research Institute |
| SPE-6.5: REAL-TIME DENOISING AND DEREVERBERATION WTIH TINY RECURRENT U-NET |
| Hyeong-Seok Choi; Seoul national university/Supertone |
| Sungjin Park; Seoul national university |
| Jie Hwan Lee; Supertone |
| Hoon Heo; Supertone |
| Dongsuk Jeon; Seoul national university |
| Kyogu Lee; Seoul national university/Supertone |
| SPE-6.6: WEIGHTED MAGNITUDE-PHASE LOSS FOR SPEECH DEREVERBERATION |
| Jingshu Zhang; University of Surrey |
| Mark Plumbley; University of Surrey |
| Wenwu Wang; University of Surrey |