# Looking to Listen: Audio-Visual Speech Separation

https://blog.cynexia.com/looking-to-listen-audio-visual-speech-separation

Author: [Rob Aleck](https://blog.cynexia.com/pages/about) · https://github.com/mnbf9rca · https://www.linkedin.com/in/robertaleck/ · https://family-foqos.app/

Published: 2018-05-07
Categories: LinkedIn cross-post


Very interesting approach by Google’s researchers to the “cocktail party problem”. The team trained a CNN to determine which person is speaking in a video with multiple overlapping sounds, and to amplify that speech while reducing other noise. Applications include better automated subtitles, and improved hearing aids. [https://research.googleblog.com/2018/04/looking-to-listen-audio-visual-speech.htmlhttps://research.googleblog.com/2018/04/looking-to-listen-audio-visual-speech.html](<https://research.google/blog/looking-to-listen-audio-visual-speech-separation/>)Posted by Inbar Mosseri and Oran Lang, Software Engineers, Google Research   People are remarkably good at focusing their attention on a par...