A simpler singing synthesis system

A simpler singing synthesis system

New system is the first to use an attention-based sequence-to-sequence model, dispensing with separate models for features such as vibrato and phoneme durations.

2 mentions: @AmazonScience@peteskomoroch
Date: 2020/10/16 13:00

Referring Tweets

@peteskomoroch Simplifying singing synthesis with an attention-based sequence-to-sequence model t.co/IPSSoAklrE
@AmazonScience At @interspeech20, Amazon researchers will present a new system for producing synthetic singing that's both simpler and more natural sounding than its predecessors. As input, it takes just a music score with lyrics. #AmazonScience #Interspeech2020 t.co/xJUYiSUXMY

Related Entries

Read more Amazon scientists author popular deep-learning book
0 users, 2 mentions 2020/05/07 12:57
Read more Amazon making online machine learning courses available for free
1 users, 32 mentions 2020/08/12 16:00
Read more Amazon making online machine learning courses available for free
0 users, 42 mentions 2020/08/12 16:00
Read more Amazon team takes first place in Interspeech 2020 Deep Noise Suppression Challenge
1 users, 2 mentions 2020/08/20 15:25
Read more Columbia Engineering and Amazon announce creation of New York research center - Amazon Science
0 users, 2 mentions 2020/09/22 12:56