[1910.13069] Disentangling Timbre and Singing Style with Multi-singer Singing Synthesis Systemopen searchopen navigation menucontact arXivarXiv Twitter

In this study, we define the identity of the singer with two independent concepts - timbre and singing style - and propose a multi-singer singing synthesis system that can model them separately. To this end, we extend our single-singer model into a multi-singer model in the following ways: first, we design a singer identity encoder that can adequately reflect the identity of a singer. Second, we use encoded singer identity to condition the two independent decoders that model timbre and singing style, respectively. Through a user study with the listening tests, we experimentally verify that the proposed framework is capable of generating a natural singing voice of high quality while independently controlling the timbre and singing style. Also, by using the method of changing singing styles while fixing the timbre, we suggest that our proposed network can produce a more expressive singing voice.

1 mentions: @keunwoochoi
Date: 2020/05/18 02:21

Referring Tweets

@keunwoochoi t.co/hgfCBMnRSU The structure of separate formant mask decoder and pitch skeleton decoder, the singer identity embedding is used to control two different aspects of the synthesized vocal - formant (timbre) and pitch skeleton (singing style). By @92HsChoi #icassp2020

Related Entries

Read more [2002.07016] Meta-learning Extractors for Music Source Separationopen searchopen navigation menucont...
0 users, 1 mentions 2020/05/18 02:21
Read more GitHub - keunwoochoi/kapre at kapre-0.3.2
0 users, 1 mentions 2020/08/30 14:21
Read more Tensorflow2 Keras – Custom loss function and metric classes for multi task learning – Keunwoo Choi
0 users, 1 mentions 2020/09/29 01:09
Read more [2010.14805] Large-Scale MIDI-based Composer Classificationopen searchopen navigation menucontact ar...
0 users, 1 mentions 2020/10/29 02:21
Read more GitHub - keunwoochoi/music4all_contrib
0 users, 1 mentions 2020/12/09 00:53