Vowel-Based Voice Conversion and Its Application to Singing-Voice Manipulation

Yoshida Y, Nisimura R, Irino T, Kawahara H. Vowel-Based Voice Conversion and Its Application to Singing-Voice Manipulation. In: AES Conference: 35th International Conference: Audio for Games. Audio Engineering Society; 2009. Paper 6. Available from: https://aes.org/publications/elibrary-page/?id=15160

@inproceedings{Yoshida2009_15160,
  author = {Yoshida, Yuri and Nisimura, Ryuichi and Irino, Toshio and Kawahara, Hideki},
  title = {{Vowel-Based Voice Conversion and Its Application to Singing-Voice Manipulation}},
  booktitle = {AES Conference: 35th International Conference: Audio for Games},
  note = {Paper 6},
  year = {2009},
  month = feb,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15160}
}

TY  - CPAPER
TI  - Vowel-Based Voice Conversion and Its Application to Singing-Voice Manipulation
AU  - Yoshida, Yuri
AU  - Nisimura, Ryuichi
AU  - Irino, Toshio
AU  - Kawahara, Hideki
T2  - AES Conference: 35th International Conference: Audio for Games
M1  - Paper 6
PY  - 2009
DA  - 2009/02/06
UR  - https://aes.org/publications/elibrary-page/?id=15160
PB  - Audio Engineering Society
LA  - en
AB  - A novel and light-weight voice conversion method is applied to manipulate a singer's identity and singing style in realtime. The proposed method is based on a non-linear spectral morphing method that uses proximity information for vowel templates of the source and the target singing materials. The proposed method is based on the STRAIGHT speech analysis, modification and resynthesis system, and it yields highly natural manipulated sounds. To deal with the difficulties in applying our vowel-based voice conversion method to singing voices, singular-value decomposition and robust statistical measures are introduced to handle the huge variability of vowel spectra and fundamental frequencies in singing voices. Distance measures for preparing vowel templates and calculating proximity information are designed based on a psychophysical frequency scale, the equivalent rectangular band, ERB_N rate.
ER  -