| 💻 | Technology article work in progress. For information on how to help, see the guidelines. More subjects categorized here. |
💻 |
Sinsy (Singing Voice Synthesis System) (しぃんしぃ) is an online HMM-based singing voice synthesis system by the Nagoya Institute of Technology that was created under the Modified BSD license.
History[]
The synthesizer is free to use, but will only generate tracks up to 5 minutes. The user uploads data in the MusicXML format, which the Sinsy website reads to output a WAV file of the generated voice. Gender factor, vibrato intensity, and pitch shift can be adjusted prior to output.[1]
MusicXML files can be made in Symphony Pro, Cadencii, MuseScore, and finale NotePad.
Some users have praised Sinsy for its realism. This can be attributed to Sinsy's voice source being a TTS (specifically, HTS, also by the Nagoya Institute of Technology), a process known for producing human-like results.
As of December 25, 2013 the official creators of the Sinsy are Keiichi Tokuda (Producer and designer), Keiichiro Oura (Design and Development), Nakamura Kazuhiro (Development and Main Maintainer), and Yoshihiko Nankaku.
Releases[]
Hidden Markov Model Voice Models
Deep Neural Network Voice Models
References[]
External links[]
Official[]
Articles[]
[]
| ||||||||||