SPE-34.2
VADOI: VOICE-ACTIVITY-DETECTION OVERLAPPING INFERENCE FOR END-TO-END LONG-FORM SPEECH RECOGNITION
Jinhan Wang, University of California, Los Angeles, United States of America; Xiaosu Tong, Jinxi Guo, Di He, Roland Maas, Amazon, United States of America
Session:
Speech Recognition: General Topics III
Track:
Speech and Language Processing
Location:
Gather Area C
Presentation Time:
Tue, 10 May, 20:00 - 20:45 China Time (UTC +8)
Tue, 10 May, 12:00 - 12:45 UTC
Tue, 10 May, 12:00 - 12:45 UTC
Session Chair:
Samuel Thomas, IBM
Session SPE-34
SPE-34.1: PRIVACY ATTACKS FOR AUTOMATIC SPEECH RECOGNITION ACOUSTIC MODELS IN A FEDERATED LEARNING FRAMEWORK
Natalia Tomashenko, Salima Mdhaffar, Yannick Estève, Jean-Francois Bonastre, University of Avignon, France; Marc Tommasi, University of Lille, France
SPE-34.2: VADOI: VOICE-ACTIVITY-DETECTION OVERLAPPING INFERENCE FOR END-TO-END LONG-FORM SPEECH RECOGNITION
Jinhan Wang, University of California, Los Angeles, United States of America; Xiaosu Tong, Jinxi Guo, Di He, Roland Maas, Amazon, United States of America
SPE-34.3: TORCHAUDIO: BUILDING BLOCKS FOR AUDIO AND SPEECH PROCESSING
Yao-Yuan Yang, University of California, San Diego, United States of America; Moto Hira, Zhaoheng Ni, Artyom Astafurov, Caroline Chen, Christian Puhrsch, Dmitriy Genzel, Donny Greenberg, Edward Yang, Jason Lian, Jeff Hwang, Ji Chen, Soumith Chintala, Vincent Quenneville-Bélair, Facebook AI, United States of America; David Pollack, Solvemate Gmbh, Germany; Peter Goldsborough, Anduril Industries, United States of America; Sean Narenthiran, Grid AI Labs, United Kingdom of Great Britain and Northern Ireland; Shinji Watanabe, Carnegie Mellon University, United States of America
SPE-34.4: UNSUPERVISED MODEL ADAPTATION FOR END-TO-END ASR
Ganesh Sivaraman, Ricardo Casal, Matthew Garland, Elie Khoury, Pindrop, United States of America
SPE-34.5: SPEECH RECOGNITION USING BIOLOGICALLY-INSPIRED NEURAL NETWORKS
Thomas Bohnstingl, Ayush Garg, Stanisław Woźniak, Evangelos Eleftheriou, Angeliki Pantazi, IBM Research Zurich, Switzerland; George Saon, IBM Research AI, United States of America