SPE-P15: Speech Recognition: Adaptation |
| Session Type: Poster |
| Time: Thursday, 7 May, 16:30 - 18:30 |
| Location: On-Demand |
| Virtual Session: View on Virtual Platform |
| Session Chairs: Sriram Ganapathy, Indian Institute of Science (IISc), Bangalore and Farzaneh S. Fard, Fluent.ai Inc |
| SPE-P15.1: UNSUPERVISED SPEAKER ADAPTATION USING ATTENTION-BASED SPEAKER MEMORY FOR END-TO-END ASR |
| Leda Sari; University of Illinois at Urbana-Champaign |
| Niko Moritz; Mitsubishi Electric Research Laboratories (MERL) |
| Takaaki Hori; Mitsubishi Electric Research Laboratories (MERL) |
| Jonathan Le Roux; Mitsubishi Electric Research Laboratories (MERL) |
| SPE-P15.2: L-VECTOR: NEURAL LABEL EMBEDDING FOR DOMAIN ADAPTATION |
| Zhong Meng; Microsoft Corporation |
| Hu Hu; Georgia Institute of Technology |
| Jinyu Li; Microsoft Corporation |
| Changliang Liu; Microsoft Corporation |
| Yan Huang; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| Chin-Hui Lee; Georgia Institute of Technology |
| SPE-P15.3: ACOUSTIC MODEL ADAPTATION FOR PRESENTATION TRANSCRIPTION AND INTELLIGENT MEETING ASSISTANT SYSTEMS |
| Yan Huang; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SPE-P15.4: USING PERSONALIZED SPEECH SYNTHESIS AND NEURAL LANGUAGE GENERATOR FOR RAPID SPEAKER ADAPTATION |
| Yan Huang; Microsoft Corporation |
| Lei He; Microsoft Corporation |
| Wenning Wei; Microsoft Corporation |
| William Gale; Microsoft Corporation |
| Jinyu Li; Microsoft Corporation |
| Yifan Gong; Microsoft Corporation |
| SPE-P15.5: ATTENTION-BASED GATED SCALING ADAPTIVE ACOUSTIC MODEL FOR CTC-BASED SPEECH RECOGNITION |
| Fenglin Ding; University of Science and Technology of China |
| Wu Guo; University of Science and Technology of China |
| Li-Rong Dai; University of Science and Technology of China |
| Jun Du; University of Science and Technology of China |
| SPE-P15.6: ADAPTIVE KNOWLEDGE DISTILLATION BASED ON ENTROPY |
| Kisoo Kwon; Samung Electronics |
| Hwidong Na; Samung Electronics |
| Hoshik Lee; Samung Electronics |
| Nam Soo Kim; Seoul national university |
| SPE-P15.7: UNSUPERVISED PRETRAINING TRANSFERS WELL ACROSS LANGUAGES |
| Morgane Rivière; Facebook |
| Armand Joulin; Facebook |
| Pierre-Emmanuel Mazaré; Facebook |
| Emmanuel Dupoux; Facebook |
| SPE-P15.8: INCREMENTAL SEMI-SUPERVISED LEARNING FOR MULTI-GENRE SPEECH RECOGNITION |
| Banriskhem K. Khonglah; Idiap Research Institute |
| Srikanth Madikeri; Idiap Research Institute |
| Subhadeep Dey; Idiap Research Institute |
| Hervé Bourlard; Idiap Research Institute |
| Petr Motlicek; Idiap Research Institute |
| Jayadev Billa; Information Sciences Institute, University of Southern California |
| SPE-P15.9: SOURCE DOMAIN DATA SELECTION FOR IMPROVED TRANSFER LEARNING TARGETING DYSARTHRIC SPEECH RECOGNITION |
| Feifei Xiong; University of Sheffield |
| Jon Barker; University of Sheffield |
| Zhengjun Yue; University of Sheffield |
| Heidi Christensen; University of Sheffield |
| SPE-P15.10: STUDY OF FORMANT MODIFICATION FOR CHILDREN ASR |
| Hemant Kumar Kathania; Aalto University |
| Sudarsana Reddy Kadiri; Aalto University |
| Paavo Alku; Aalto University |
| Mikko Kurimo; Aalto University |
| SPE-P15.11: PSEUDO LIKELIHOOD CORRECTION TECHNIQUE FOR LOW RESOURCE ACCENTED ASR |
| Avni Rajpal; Indian Institute of Science |
| Achuth Rao M V; Indian Institute of Science |
| Chiranjeevi Yarra; Indian Institute of Science |
| Ritu Aggarwal; Indian Institute of Science |
| Prasanta Kumar Ghosh; Indian Institute of Science |
| SPE-P15.12: LIBRI-ADAPT: A NEW SPEECH DATASET FOR UNSUPERVISED DOMAIN ADAPTATION |
| Akhil Mathur; University College London and Nokia Bell Labs |
| Fahim Kawsar; Nokia Bell Labs |
| Nadia Berthouze; University College London |
| Nicholas Lane; University of Oxford |