ASMSP_L6: Robust representations and model adaptation for audio analysis |
| Session Type: Lecture |
| Time: Thursday, September 1, 11:00 - 12:40 |
| Location: Baltic + Aegean |
| Session Chair: Milan Sečujski, University of Novi Sad |
| ASMSP_L6.1: A STUDY ON ROBUSTNESS TO PERTURBATIONS FOR REPRESENTATIONS OF ENVIRONMENTAL SOUND |
| Sangeeta Srivastava, Anish Arora, The Ohio State University, United States; Ho-Hsiang Wu, Joao Rulff, Magdalena Fuentes, Claudio Silva, Juan Bello, New York University, United States; Mark Cartwright, New Jersey Institute of Technology, United States |
| ASMSP_L6.2: NON-INTRUSIVE SIGNAL ANALYSIS FOR ROOM ADAPTATION OF ASR MODELS |
| Ge Li, Dushyant Sharma, Nuance Communications Inc, Canada; Patrick Naylor, Imperial College London, United Kingdom |
| ASMSP_L6.3: MULTIROOM SPEECH EMOTION RECOGNITION |
| Erez Shalev, Israel Cohen, Technion, Israel Institute of Technology, Israel |
| ASMSP_L6.4: NOISE, DEVICE AND ROOM ROBUSTNESS METHODS FOR PRONUNCIATION ERROR DETECTION |
| Ville-Veikko Eklund, Aleksandr Diment, Tuomas Virtanen, Tampere University, Finland |
| ASMSP_L6.5: ACOUSTIC MODEL ADAPTATION IN REVERBERANT CONDITIONS USING MULTI-TASK LEARNED EMBEDDINGS |
| Aditya Raikar, Ashish Panda, Sunil Kumar Kopparapu, Tata Consultancy Services, India; Meet Soni, Samsung Research Institute, Bangalore, India |