SPE-68.2
LEARNABLE NONLINEAR COMPRESSION FOR ROBUST SPEAKER VERIFICATION
Xuechen Liu, University of Eastern Finland & Inria, Finland; Md Sahidullah, Inria, France; Tomi Kinnunen, University of Eastern Finland, Finland
Session:
Speaker Recognition IX: Single and Multi Channel
Track:
Speech and Language Processing
Location:
Gather Area B
Presentation Time:
Thu, 12 May, 21:00 - 21:45 China Time (UTC +8)
Thu, 12 May, 13:00 - 13:45 UTC
Thu, 12 May, 13:00 - 13:45 UTC
Session Chair:
Hagai Aronowitz, IBM Research AI
Session SPE-68
SPE-68.1: MULTI-FEATURE INTEGRATION FOR SPEAKER EMBEDDING EXTRACTION
Sreekanth Sankala, Shaik Mohammad Rafi B, Sri Rama Murty K, Indian Institute of Technology Hyderabad, India
SPE-68.2: LEARNABLE NONLINEAR COMPRESSION FOR ROBUST SPEAKER VERIFICATION
Xuechen Liu, University of Eastern Finland & Inria, Finland; Md Sahidullah, Inria, France; Tomi Kinnunen, University of Eastern Finland, Finland
SPE-68.3: FINE-TUNING WAV2VEC2 FOR SPEAKER RECOGNITION
Nik Vaessen, David A. van Leeuwen, Radboud University, Netherlands
SPE-68.4: GRAPH ATTENTIVE FEATURE AGGREGATION FOR TEXT-INDEPENDENT SPEAKER VERIFICATION
Hye-jin Shim, Jungwoo Heo, Ha-Jin Yu, University of Seoul, Korea, Republic of; Jae-han Park, Ga-Hui Lee, KT Corporation, Korea, Republic of
SPE-68.5: MULTISV: DATASET FOR FAR-FIELD MULTI-CHANNEL SPEAKER VERIFICATION
Ladislav Mošner, Oldřich Plchot, Lukáš Burget, Jan Černocký, Faculty of Information Technology, Brno University of Technology, Czechia
SPE-68.6: MULTI-CHANNEL SPEAKER VERIFICATION WITH CONV-TASNET BASED BEAMFORMER
Ladislav Mošner, Oldřich Plchot, Lukáš Burget, Jan Černocký, Faculty of Information Technology, Brno University of Technology, Czechia