MLSP-P15: Audio and Speech Applications |
| Session Type: Poster |
| Time: Thursday, May 16, 18:00 - 20:00 |
| Location: Poster Area G, East Landing, First Floor |
| Session Chair: Zhang Tao, Starkey Hearing Technologies |
| MLSP-P15.1: SPEECH SUPER RESOLUTION GENERATIVE ADVERSARIAL NETWORK |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Sefik Emre Eskimez; University of Rochester |
| Kazuhito Koishida; Microsoft Corporation |
| MLSP-P15.2: NOVEL METRIC LEARNING FOR NON-PARALLEL VOICE CONVERSION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Nirmesh Shah; DA-IICT, Gandhinagar |
| Hemant Patil; DA-IICT, Gandhinagar |
| MLSP-P15.3: DEEP LEARNING FOR CLASSROOM ACTIVITY DETECTION FROM AUDIO |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Robin Cosbey; Western Washington University |
| Allison Wusterbarth; Conversica |
| Brian Hutchinson; Western Washington University |
| MLSP-P15.4: TRANSFERABLE POSITIVE/NEGATIVE SPEECH EMOTION RECOGNITION VIA CLASS-WISE ADVERSARIAL DOMAIN ADAPTATION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Hao Zhou; The University of Manchester |
| Ke Chen; The University of Manchester |
| MLSP-P15.5: ATTITUDE RECOGNITION USING MULTI-RESOLUTION COCHLEAGRAM FEATURES |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Fasih Haider; The University of Edinburgh |
| Saturnino Luz; The University of Edinburgh |
| MLSP-P15.6: TO REVERSE THE GRADIENT OR NOT: AN EMPIRICAL COMPARISON OF ADVERSARIAL AND MULTI-TASK LEARNING IN SPEECH RECOGNITION |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Yossi Adi; Bar-Ilan University |
| Neil Zeghidour; Facebook AI Research and CoML, ENS/INRIA |
| Ronan Collobert; Facebook AI Research |
| Nicolas Usunier; Facebook AI Research |
| Vitaliy Liptchinsky; Facebook AI Research |
| Gabriel Synnaeve; Facebook AI Research |
| MLSP-P15.7: TOWARDS AUTOMATIC METHODS TO DETECT ERRORS IN TRANSCRIPTIONS OF SPEECH RECORDINGS |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Jinyi Yang; Johns Hopkins University |
| Lucas Ondel; Brno University of Technology |
| Vimal Manohar; Johns Hopkins University |
| Hynek Hermansky; Johns Hopkins University |
| MLSP-P15.8: ONLINE SINGING VOICE SEPARATION USING A RECURRENT ONE-DIMENSIONAL U-NET TRAINED WITH DEEP FEATURE LOSSES |
| Manuscript Link: Click here to view manuscript on IEEE Xplore |
| Clement Doire; Audionamix |