VOCALOID Commercial singing synthesizer based on sample concatenation

1
VOCALOIDCommercial singing synthesizer based on
sample concatenation

• Hideki Kenmochi, Hayato Ohshita
• Center for Advanced Sound Technologies, Yamaha
  Corporation, Japan

2
System Diagram

• Diphones
• sustained portions
• (Multiple pitches)

• Timing adjustment
• Pitch transposition
• Timbre manipulation

3
Synthesis Score
Sing a song s I N _at_ s Q N
4
Concatenation
s I
I
I N
Use as it is
Fluctuations from sustained portion added
Timbre(Spectralenvelope)
Last Frame
First Frame
Interpolation
LocalSpectrum
5
Pitch transposition timbre manipulation
6
Pitch transposition timbre manipulation
7
Score Editor

• Dedicated environment for singing synthesis
• Note / Lyric input
• Vibrato setting
• Control over synthesis parameters

8
Piano-roll editor
Control Track
9
(No Transcript)
10
(No Transcript)
11
(No Transcript)
12
(No Transcript)
13
(No Transcript)
14
(No Transcript)
15
(No Transcript)
16
Realtime keyboard performance mode

• Lyrics input in advance
• Keyboard triggers note

Video Clip
17
VOCALOID Products

• Version 1 (released in 2004)
• Version 2 (released in 2007)

Meiko
Kaito
LEON
LOLA
MIRIAM
Big-AL
Sweet ANN
Prima
Miku
18
Audio Demos

• Amazing Grace
• Compulsory

19
Acknowledgements

• The basic signal processing technique used in
  Vocaloid is developed though a joint research
  project between Yamaha Corporation and Music
  Technology Group (MTG), Universitari Pompeu
  Fabra, Barcelona.
• The authors would like to thank the staff at MTG,
  especially to Mr. Jordi Bonada and Dr. Alex
  Loscos, for their contribution to Vocaloid.

20
Dank voor uw aandacht.