SLP-L10: Speaker Diarization I
Wed, 17 Apr, 08:20 - 10:20 (UTC +9)
Location: Room E3
Session Type: Lecture
Session Co-Chairs: Man Wai Mak, The Hong Kong Polytechnic University and Leibny Garcia Perera, Johns Hopkins University
Track: Speech and Language Processing
Click the to view the manuscript on IEEE Xplore Open Preview
Wed, 17 Apr, 08:20 - 08:40 (UTC +9)
 

SLP-L10.1: DISCRIMINATIVE TRAINING OF VBX DIARIZATION
Dominik Klement, Mireia Diez, Federico Landini, Lukáš Burget, Anna Silnova, Brno University of Technology, Czechia; Marc Delcroix, Naohiro Tawara, NTT Corporation, Japan
Wed, 17 Apr, 08:40 - 09:00 (UTC +9)
 

SLP-L10.2: Prompt-driven Target Speech Diarization
Yidi Jiang, National University of Singapore, Singapore; Zhengyang Chen, Shanghai Jiao Tong University, China; Ruijie Tao, National University of Singapore, Singapore; Liqun Deng, Huawei Noah's Ark Lab, China; Yanmin Qian, Shanghai Jiao Tong University, China; Haizhou Li, The Chinese University of Hong Kong, Shenzhen, China
Wed, 17 Apr, 09:00 - 09:20 (UTC +9)
 

SLP-L10.3: DIACORRECT: ERROR CORRECTION BACK-END FOR SPEAKER DIARIZATION
Jiangyu Han, Federico Landini, Johan Rohdin, Mireia Diez, Lukas Burget, Brno University of Technology, Czechia; Yuhang Cao, Heng Lu, Ximalaya Inc., ShangHai, China, China; Jan Cernocky, Brno University of Technology, Czechia
Wed, 17 Apr, 09:20 - 09:40 (UTC +9)
 

SLP-L10.4: ENHANCING SPEAKER DIARIZATION WITH LARGE LANGUAGE MODELS: A CONTEXTUAL BEAM SEARCH APPROACH
Tae Jin, Kunal Dhawan, Nithin Koluguri, Jagadeesh Balam, NVIDIA, United States of America
Wed, 17 Apr, 09:40 - 10:00 (UTC +9)
 

SLP-L10.5: JOINT INFERENCE OF SPEAKER DIARIZATION AND ASR WITH MULTI-STAGE INFORMATION SHARING
Weiqing Wang, Danwei Cai, Duke University, United States of America; Ming Cheng, Ming Li, Duke Kunshan University, China
Wed, 17 Apr, 10:00 - 10:20 (UTC +9)
 

SLP-L10.6: ONE MODEL TO RULE THEM ALL ? TOWARDS END-TO-END JOINT SPEAKER DIARIZATION AND SPEECH RECOGNITION
Samuele Cornell, Università Politecnica delle Marche, Italy; Jee-weon Jung, Shinji Watanabe, Carnegie Mellon University, United States of America; Stefano Squartini, Università Politecnica delle Marche, Italy