Technical Program
AASP-L5: Speech Separation and Enhancement |
| Session Type: Lecture |
| Time: Thursday, May 30, 08:00 - 10:00 |
| Location: Room 110 |
| Session Chair: Sharon Gannot, Bar-Ilan University, Israel |
| AASP-L5.1: JOINT CONSTRAINED MAXIMUM LIKELIHOOD REGRESSION FOR OVERLAPPING SPEECH RECOGNITION |
| Kenichi Kumatani; Spansion Inc. |
| Rita Singh; Carnegie Mellon University |
| Friedrich Faubel; Saarland University |
| John McDonough; Carnegie Mellon University |
| Youssef Oualil; Saarland University |
| AASP-L5.2: THE SECOND ‘CHIME’ SPEECH SEPARATION AND RECOGNITION CHALLENGE: DATASETS, TASKS AND BASELINES |
| Emmanuel Vincent; INRIA |
| Jon Barker; University of Sheffield |
| Shinji Watanabe; Mitsubishi Electric Research Laboratories (MERL) |
| Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL) |
| Francesco Nesta; FBK-Irst |
| Marco Matassoni; FBK-Irst |
| AASP-L5.3: INTEGRATING NOISE ESTIMATION AND FACTORIZATION-BASED SPEECH SEPARATION: A NOVEL HYBRID APPROACH |
| Cyril Joder; Technische Universität München |
| Felix Weninger; Technische Universität München |
| David Virette; Huawei European Research Center |
| Björn Schuller; Technische Universität München |
| AASP-L5.4: LEARNABLE LOW RANK SPARSE MODELS FOR SPEECH DENOISING |
| Pablo Sprechmann; Duke University |
| Alex Bronstein; Tel Aviv University |
| Michael Bronstein; Università della Svizzera italiana |
| Guillermo Sapiro; Duke University |
| AASP-L5.5: UNIVERSAL SPEECH MODELS FOR SPEAKER INDEPENDENT SINGLE CHANNEL SOURCE SEPARATION |
| Dennis Sun; Stanford University |
| Gautham Mysore; Adobe |
| AASP-L5.6: USING DYNAMIC CONDITIONAL RANDOM FIELD ON SINGLE-MICROPHONE SPEECH SEPARATION |
| Yu Ting Yeung; The Chinese University of Hong Kong |
| Tan Lee; The Chinese University of Hong Kong |
| Cheung-Chi Leung; Agency for Science, Technology and Research |