ASMSP_P6: Speech recognition and analysis |
| Session Type: Poster |
| Time: Friday, September 2, 11:00 - 12:40 |
| Location: Poster Area 2 |
| Session Chair: Elena Menyaylenko, Apple Inc |
| ASMSP_P6.1: INVESTIGATING NEURAL REPRESENTATION LEARNING WITHIN CONVOLUTIONAL TRANSFORMERS FOR END-TO-END ASR |
| Anna Ollerenshaw, Md Asif Jalal, Thomas Hain, University of Sheffield, United Kingdom |
| ASMSP_P6.2: TRANSFORMER MODEL COMPRESSION FOR END-TO-END SPEECH RECOGNITION ON MOBILE DEVICES |
| Leila Ben Letaifa, Jean-Luc Rouas, Laboratoire Bordelais de Recherche en Informatique, France |
| ASMSP_P6.3: FEW-SHOT LEARNING FOR E2E SPEECH RECOGNITION: ARCHITECTURAL VARIANTS FOR SUPPORT SET GENERATION |
| Dhanya Eledath, Tirthankar Banerjee, V Ramasubramanian, International Institute of Information Technology Bangalore (IIITB), India; Narasimha Rao Thurlapati, V Pavithra, Samsung R&D Institute, Bangalore (SRIB), India |
| ASMSP_P6.4: FILTER-BASED DISCRIMINATIVE AUTOENCODERS FOR CHILDREN SPEECH RECOGNITION |
| Chiang-Lin Tai, Hung-Shin Lee, Yu Tsao, Hsin-Min Wang, Academia Sinica, Taiwan |
| ASMSP_P6.5: OVERCOMING DATA SPARSITY IN AUTOMATIC TRANSCRIPTION OF DICTATED MEDICAL FINDINGS |
| Edvin Pakoci, Darko Pekar, AlfaNum Speech Technologies, Serbia; Branislav Popović, Milan Sečujski, Vlado Delić, University of Novi Sad, Faculty of Technical Sciences, Serbia |
| ASMSP_P6.6: CONTINUAL LEARNING FOR MONOLINGUAL END-TO-END AUTOMATIC SPEECH RECOGNITION |
| Steven Vander Eeckt, Hugo Van hamme, KU Leuven, Belgium |
| ASMSP_P6.7: SEMI-SUPERVISED ONLINE SPEAKER DIARIZATION USING VECTOR QUANTIZATION WITH ALTERNATIVE CODEBOOKS |
| Mahmoud El-Hindi, Michael Muma, Abdelhak M Zoubir, Technische Universität Darmstadt,, Germany |