2021 IEEE International Conference on Acoustics, Speech and Signal Processing
6-11 June 2021 • Toronto, Ontario, Canada
Extracting Knowledge from Information
SPE-18: Speech Enhancement 4: Multi-channel Processing |
| Session Type: Poster |
| Time: Wednesday, 9 June, 14:00 - 14:45 |
| Location: Gather.Town |
| Virtual Session: View on Virtual Platform |
| Session Chair: Dorothea Kolossa, Ruhr-Universität Bochum |
| SPE-18.1: NEURAL NETWORK-BASED VIRTUAL MICROPHONE ESTIMATOR |
| Tsubasa Ochiai; NTT Corporation |
| Marc Delcroix; NTT Corporation |
| Tomohiro Nakatani; NTT Corporation |
| Rintaro Ikeshita; NTT Corporation |
| Keisuke Kinoshita; NTT Corporation |
| Shoko Araki; NTT Corporation |
| SPE-18.2: JOINT MAXIMUM LIKELIHOOD ESTIMATION OF POWER SPECTRAL DENSITIES AND RELATIVE ACOUSTIC TRANSFER FUNCTIONS FOR ACOUSTIC BEAMFORMING |
| Poul Hoang; Demant A/S |
| Zheng-Hua Tan; Aalborg University |
| Jan Mark de Han; Demant A/S |
| Jesper Jensen; Demant A/S |
| SPE-18.3: CUE-PRESERVING MMSE FILTER WITH BAYESIAN SNR MARGINALIZATION FOR BINAURAL SPEECH ENHANCEMENT |
| Stefan Thaleiser; Ruhr-Universität Bochum |
| Gerald Enzner; Ruhr-Universität Bochum |
| SPE-18.4: BLIND AND NEURAL NETWORK-GUIDED CONVOLUTIONAL BEAMFORMER FOR JOINT DENOISING, DEREVERBERATION, AND SOURCE SEPARATION |
| Tomohiro Nakatani; NTT Corporation |
| Rintaro Ikeshita; NTT Corporation |
| Keisuke Kinoshita; NTT Corporation |
| Hiroshi Sawada; NTT Corporation |
| Shoko Araki; NTT Corporation |
| SPE-18.5: REAL-TIME SPEECH ENHANCEMENT FOR MOBILE COMMUNICATION BASED ON DUAL-CHANNEL COMPLEX SPECTRAL MAPPING |
| Ke Tan; The Ohio State University |
| Xueliang Zhang; Inner Mongolia University |
| DeLiang Wang; The Ohio State University |
| SPE-18.6: DON’T SHOOT BUTTERFLY WITH RIFLES: MULTI-CHANNEL CONTINUOUS SPEECH SEPARATION WITH EARLY EXIT TRANSFORMER |
| Sanyuan Chen; Harbin Institute of Technology |
| Yu Wu; Microsoft Corporation |
| Zhuo Chen; Microsoft Corporation |
| Takuya Yoshioka; Microsoft Corporation |
| Shujie Liu; Microsoft Corporation |
| Jinyu Li; Microsoft Corporation |
| Xiangzhan Yu; Harbin Institute of Technology |