Marc Delcroix (NTT): Target Speaker Extraction with SpeakerBeam

When:
July 3, 2018 @ 2:00 pm – 3:00 pm
2018-07-03T14:00:00-04:00
2018-07-03T15:00:00-04:00
Where:
Hackerman 320
Abstract

Automatic speech recognition has greatly progressed in recent years and is being used more and more in challenging conditions. However, the performance of current systems degrades when several people speak at the same time in conversations or when TV is on in the background. In this talk, we will present our recent investigation on target speaker extraction using SpeakerBeam. SpeakerBeam is a neural network that extracts speech from a target speaker out of a mixture of speech signals. SpeakerBeam uses a short adaptation utterance containing only the voice of the target speaker to compute the characteristics of his/her voice and then use these characteristics to adapt the neural network so that it can focus on extracting the voice of that target speaker.

 

BIO

See homepage.

Johns Hopkins University

Johns Hopkins University, Whiting School of Engineering

Center for Language and Speech Processing
Hackerman 226
3400 North Charles Street, Baltimore, MD 21218-2680

Center for Language and Speech Processing