AUD-L2: Deep Learning for Source Separation |
| Session Type: Lecture |
| Time: Tuesday, 5 May, 16:30 - 18:30 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chair: Minje Kim, Indiana University Bloomington |
| AUD-L2.1: TWO-STEP SOUND SOURCE SEPARATION: TRAINING ON LEARNED LATENT TARGETS |
| Efthymios Tzinis; University of Illinois at Urbana-Champaign |
| Shrikant Venkataramani; University of Illinois at Urbana-Champaign |
| Zhepei Wang; University of Illinois at Urbana-Champaign |
| Cem Subakan; Mila-Quebec Artificial Intelligence Institute |
| Paris Smaragdis; University of Illinois at Urbana-Champaign, Adobe Research |
| AUD-L2.2: A MULTI-PHASE GAMMATONE FILTERBANK FOR SPEECH SEPARATION VIA TASNET |
| David Ditter; Universität Hamburg |
| Timo Gerkmann; Universität Hamburg |
| AUD-L2.3: IMPROVING VOICE SEPARATION BY INCORPORATING END-TO-END SPEECH RECOGNITION |
| Naoya Takahashi; Sony Corporation |
| Mayank Singh; Indian Institute of Technology Bombay |
| Sakya Basak; Indian Institute of Science |
| Parthasaarathy Sudarsanam; Sony India Software Centre |
| Sriram Ganapathy; Indian Institute of Science |
| Yuki Mitsufuji; Sony Corporation |
| AUD-L2.4: DUAL-PATH RNN: EFFICIENT LONG SEQUENCE MODELING FOR TIME-DOMAIN SINGLE-CHANNEL SPEECH SEPARATION |
| Yi Luo; Columbia University |
| Zhuo Chen; Microsoft |
| Takuya Yoshioka; Microsoft |
| AUD-L2.5: CONTROLLING THE PERCEIVED SOUND QUALITY FOR DIALOGUE ENHANCEMENT WITH DEEP LEARNING |
| Christian Uhle; Fraunhofer Institute for Integrated Circuits IIS |
| Matteo Torcoli; Fraunhofer Institute for Integrated Circuits IIS |
| Jouni Paulus; Fraunhofer Institute for Integrated Circuits IIS |
| AUD-L2.6: UNSUPERVISED TRAINING FOR DEEP SPEECH SOURCE SEPARATION WITH KULLBACK-LEIBLER DIVERGENCE BASED PROBABILISTIC LOSS FUNCTION |
| Masahito Togami; LINE Corporation |
| Yoshiki Masuyama; Waseda University |
| Tatsuya Komatsu; LINE Corporation |
| Yu Nakagome; Waseda University |