Recent Development of the DNN-based Singing Voice Synthesis System — Sinsy
| Autor: | Yoshihiko Nankaku, Keiichiro Oura, Kazuhiro Nakamura, Shumma Murata, Kei Hashimoto, Yukiya Hono, Keiichi Tokuda |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Computer science
Speech recognition 020206 networking & telecommunications 02 engineering and technology 01 natural sciences Vibrato Singing voice synthesis Naturalness 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Deep neural networks Singing Hidden Markov model 010301 acoustics |
| Zdroj: | APSIPA |
| DOI: | 10.23919/apsipa.2018.8659797 |
| Popis: | This paper describes a singing voice synthesis system based on deep neural networks (DNNs) named Sinsy. Singing voice synthesis systems based on hidden Markov models (HMMs) have grown in the last decade. Recently, singing voice synthesis systems based on DNNs have been proposed. It has improved the naturalness of the synthesized singing voices. In this paper, we introduce several techniques, i.e., trajectory training, a vibrato model, and a time-lag model, into the DNN-based singing voice synthesis system to synthesize the high quality singing voices. Experimental results show that the DNN-based systems with these techniques outperformed the HMM-based systems. In addition, the present paper describes the details of the on-line service for singing voice synthesis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|