Technical Paper
:
Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
TimeWednesday, 15 August 201812:13pm - 12:35pm
LocationWest Building, Room 211-214, Vancouver Convention Centre
DescriptionA trained, machine learning model that utilizes both the visual and auditory signals of an input video to separate the speech of different speakers in the video.
Authors
Ariel Ephrat
Google Inc.
Hebrew University of Jerusalem
Inbar Mosseri
Google Inc.
Oran Lang
Google Inc.
Tali Dekel
Google Inc.
Kevin Wilson
Google Inc.
Avinatan Hassidim
Google Inc.
William Freeman
Google Inc.
MIT
Michael Rubinstein
Google Inc.
Session Chair
Jernej Barbic
University of Southern California
Authors
Ariel Ephrat
Inbar Mosseri
Oran Lang
Tali Dekel
Kevin Wilson
Avinatan Hassidim
William Freeman
Michael Rubinstein
Event Type
Technical Paper
Registration Levels
F
FP
Personas
R&E