Korean Singing Voice Synthesis System based on an LSTM Recurrent Neural Network

Cited 19 time in webofscience Cited 0 time in scopus
  • Hit : 315
  • Download : 0
Singing voice synthesis (SVS) systems generate the singing voice from a musical score. Similar to the text-to-speech synthesis (TTS) field, SVS systems have also been greatly improved since the deep neural network (DNN) framework was introduced. Although they share many parts of the framework, the main difference between TTS and SVS systems is that the feature composing method, between linguistic and musical features, is important for SVS systems. In this paper, we propose a Korean SVS system based on a long-short term memory recurrent neural network (LSTM-RNN). At the feature composing stage, we propose a novel composing method, based on Korean syllable structure. At the synthesis stage, we adopt LSTM-RNN for the SVS. According to our experiments, our composed feature improved the naturalness of the voice, specifically in any part that has to be pronounced for a long time. Furthermore, LSTM-RNN outperformed the DNN based SVS system in both quantitative and qualitative evaluations.
Publisher
International Speech Communication Association
Issue Date
2018-09-04
Language
English
Citation

19th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2018), pp.1551 - 1555

DOI
10.21437/Interspeech.2018-1575
URI
http://hdl.handle.net/10203/247353
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 19 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0