Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data

Citation Author(s):: HUNG-YI LEE

Chia-Hao Shen, Janet Y. Sung, Hung-Yi Lee
Submitted by:: HUNG-YI LEE
Last updated:: 20 April 2018 - 12:59am
Document Type:: Presentation Slides
Document Year:: 2018
Event:: ICASSP 2018

Categories:: Content-Based Audio Processing

Log in to post comments

Audio2vec (v7).pptx

Audio2vec (v7).pptx (360)

Thumbs Up

CITE

QUESTIONS?