TH1.I: Speaker Diarization and Characterization |
| Session Type: Poster |
| Time: Thursday, 7 May, 09:00 - 11:00 |
| Location: On-Demand |
| Session Chairs: Paola Garcia Perera, Johns Hopkins University and Takafumi Koshinaka, NEC Corporation
|
| |
| TH1.I.1: TOWARD BETTER SPEAKER EMBEDDINGS: AUTOMATED COLLECTION OF SPEECH SAMPLES FROM UNKNOWN DISTINCT SPEAKERS |
| Minh Pham; Worcester Polytechnic Institute |
| Zeqian Li; Worcester Polytechnic Institute |
| Jacob Whitehill; Worcester Polytechnic Institute |
| |
| TH1.I.2: CHANNEL ADVERSARIAL TRAINING FOR SPEAKER VERIFICATION AND DIARIZATION |
| Chau Luu; University of Edinburgh |
| Peter Bell; University of Edinburgh |
| Steve Renals; University of Edinburgh |
| |
| TH1.I.3: PROGRESSIVE MULTI-TARGET NETWORK BASED SPEECH ENHANCEMENT WITH SNR-PRESELECTION FOR ROBUST SPEAKER DIARIZATION |
| Lei Sun; University of Science and Technology of China |
| Jun Du; University of Science and Technology of China |
| Xueyang Zhang; IFLYTEK Research |
| Tian Gao; IFLYTEK Research |
| Xin Fang; IFLYTEK Research |
| Chin-Hui Lee; Georgia Institute of Technology |
| |
| TH1.I.4: IMPROVED LARGE-MARGIN SOFTMAX LOSS FOR SPEAKER DIARISATION |
| Yassir Fathullah; University of Cambridge |
| Chao Zhang; University of Cambridge |
| Philip Woodland; University of Cambridge |
| |
| TH1.I.5: SPEAKER DIARIZATION WITH SESSION-LEVEL SPEAKER EMBEDDING REFINEMENT USING GRAPH NEURAL NETWORKS |
| Jixuan Wang; University of Toronto |
| Xiong Xiao; Microsoft |
| Jian Wu; Microsoft |
| Ranjani Ramamurthy; Microsoft |
| Frank Rudzicz; University of Toronto |
| Michael Brudno; University of Toronto |
| |
| TH1.I.6: OVERLAP-AWARE DIARIZATION: RESEGMENTATION USING NEURAL END-TO-END OVERLAPPED SPEECH DETECTION |
| Latané Bullock; Rice University |
| Hervé Bredin; LIMSI, CNRS, Univ. Paris-Sud, Universite Paris-Saclay |
| Leibny Paola Garcia Perera; Johns Hopkins University |
| |
| TH1.I.7: ON THE IMPORTANCE OF VOCAL TRACT CONSTRICTION FOR SPEAKER CHARACTERIZATION: THE WHISPERED SPEECH STUDY |
| Rohan Kumar Das; National University of Singapore |
| Haizhou Li; National University of Singapore |
| |
| TH1.I.8: PYANNOTE.AUDIO: NEURAL BUILDING BLOCKS FOR SPEAKER DIARIZATION |
| Hervé Bredin; LIMSI, CNRS, Université Paris-Saclay |
| Ruiqing Yin; LIMSI, CNRS, Université Paris-Saclay |
| Juan Manuel Coria; LIMSI, CNRS, Univ. Paris-Sud, Université Paris-Saclay |
| Gregory Gelly; LIMSI, CNRS |
| Pavel Korshunov; Idiap Research Institute |
| Marvin Lavechin; Ecole Normale Supérieure/INRIA |
| Diego Fustes; Toptal LLC |
| Hadrien Titeux; Université PSL |
| Wassim Bouaziz; Ecole Normale Supérieure/INRIA |
| Marie-Philippe Gill; Ecole de Technologie Supérieure, Université du Québec |
| |
| TH1.I.9: SPEAKER EMBEDDINGS INCORPORATING ACOUSTIC CONDITIONS FOR DIARIZATION |
| Yosuke Higuchi; Waseda University |
| Masayuki Suzuki; IBM |
| Gakuto Kurata; IBM |
| |
| TH1.I.10: SUPERVISED ONLINE DIARIZATION WITH SAMPLE MEAN LOSS FOR MULTI-DOMAIN DATA |
| Enrico Fini; PerVoice |
| Alessio Brutti; Fondazione Bruno Kessler |
| |
| TH1.I.11: INVESTIGATION OF SPECAUGMENT FOR DEEP SPEAKER EMBEDDING LEARNING |
| Shuai Wang; Shanghai Jiao Tong University |
| Johan Rohdin; Brno University of Technology |
| Oldřich Plchot; Brno University of Technology |
| Lukáš Burget; Brno University of Technology |
| Kai Yu; Shanghai Jiao Tong University |
| Jan Cernocky; Brno University of Technology |
| |