Presentation 1998/2/19
Singing Voice Synthesis System
Yuki YOSHIDA, Shin'ya NAKAJIMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We developed a singing voice synthesis system correspond to MIDI using Text-to-Speech.The system first accepts a score from a standard MIDI file as input, then pitch and duration of each musical note are extracted automatically.Next phonological series are analyzed from given lyrics, and singing voice is synthesized by waveform speech synthesis.It is played together with BGM by synchronizing with MIDI format data.In this system, users can add other information such as power modulation, speech quality modification or vibrato, and can direct the singing voice, Furthermore, if lyrics is given at two or more trucks, harmony and duet can be also performed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) singing voice synthesis / speech synthesis / waveform speech synthesis / MIDI / DTM
Paper #
Date of Issue

Conference Information
Committee SP
Conference Date 1998/2/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Singing Voice Synthesis System
Sub Title (in English)
Keyword(1) singing voice synthesis
Keyword(2) speech synthesis
Keyword(3) waveform speech synthesis
Keyword(4) MIDI
Keyword(5) DTM
1st Author's Name Yuki YOSHIDA
1st Author's Affiliation NTT Human Interface Labolatories()
2nd Author's Name Shin'ya NAKAJIMA
2nd Author's Affiliation NTT Human Interface Labolatories
Date 1998/2/19
Paper #
Volume (vol) vol.97
Number (no) 560
Page pp.pp.-
#Pages 2
Date of Issue