Oleg Zabluda's blog
Tuesday, April 17, 2018
 
Looking to Listen: Audio-Visual Speech Separation
Looking to Listen: Audio-Visual Speech Separation
"""
cocktail party effect [...] automatic speech separation — separating an audio signal into its individual speech sources — while a well-studied problem, remains a significant challenge for computers.

In “Looking to Listen at the Cocktail Party” [...] we are able to computationally produce videos in which speech of specific people is enhanced while all other sounds are suppressed. [...] on ordinary videos with a single audio track [...] We believe this capability can have a wide range of applications, from speech enhancement and recognition in videos, through video conferencing, to improved hearing aids, especially in situations where there are multiple people speaking.
"""
https://research.googleblog.com/2018/04/looking-to-listen-audio-visual-speech.html

Labels:


| |

Home

Powered by Blogger