Transferring Vocal Expression of F0 Contour Using Singing Voice Synthesizer
A system for transferring vocal expressions separately from singing voices with accompaniment to singing voice synthesizers is described. The expressions appear as fluctuations in the fundamental frequency contour of the singing voice, such as vibrato, glissando, and kobushi. The fundamental frequency contour of the singing voice is estimated using the subharmonic summation in a limited frequency range and aligned temporally to chromatic pitch sequence. Each expression is transcribed and parameterized in accordance with designed rules. Finally, the expressions are transferred to given scores on the singing voice synthesizer. Experiments demonstrated that the proposed system can transfer the vocal expressions while retaining singer’s individuality on two singing voice synthesizers: the Vocaloid and the CeVIO.
KeywordsViterbi Algorithm Musical Piece Pitch Range Music Information Retrieval Vocal Expression
Unable to display preview. Download preview PDF.
- 2.Kenmochi, H., Ohshita, H.: Vocaloid - commercial singing synthesizer based on sample concatenation. In: INTERSPEECH 2007, pp. 4009–4010 (2007)Google Scholar
- 3.Saito, T., Goto, M.: Acoustic and perceptual effects of vocal training in amateur male singing. In: INTERSPEECH 2009, pp. 832–835 (September 2009)Google Scholar
- 5.Stables, R., Athwal, C., Bullock, J.: Fundamental frequency modulation in singing voice synthesis. In: International Conference on Speech, Sound and Music Processing: Embracing Research in India, pp. 104–119 (2012)Google Scholar
- 6.Umbert, M., Bonada, J., Blaauw, M.: Generating singing voice expression contours based on unit selection. In: SMAC (July 2013)Google Scholar
- 7.Nakano, T., Goto, M.: VocaListener2: A singing synthesis system able to mimic a user’s singing in terms of voice timbre changes as well as pitch and dynamics. In: ICASSP 2011, pp. 453–456 (2011)Google Scholar
- 8.Ohishi, Y., Kameoka, H., Mochihashi, D., Kashino, K.: A stochastic model of singing voice F0 contours for characterizing expressive dynamic components. In: Proc. INTERSPEECH (September 2012)Google Scholar
- 9.Oura, K., Mase, A., Yamada, T., Muto, S., Nankaku, Y., Tokuda, K.: Recent development of the HMM-based singing voice synthesis system - Sinsy. In: Proc. ISCA Tutorial and Research Workshop on Speech Synthesis, pp. 211–216 (September 2010)Google Scholar
- 10.Saino, K., Tachibana, M., Kenmochi, H.: A singing style modeling system for singing voice synthesizers. In: Proc. INTERSPEECH, pp. 2894–2897 (September 2010)Google Scholar
- 11.Lee, S.W., Ang, S.T., Dong, M., Li, H.: Generalized F0 modelling with absolute and relative pitch features for singing voice synthesis. In: Proc. ICASSP, pp. 429–432 (March 2012)Google Scholar
- 12.Yasuraoka, N., Abe, T., Itoyama, K., Takahashi, T., Ogata, T., Okuno, H.G.: Changing timbre and phrase in existing musical performances as you like. In: ACM Multimedia 2009, p. 10 (2009)Google Scholar
- 15.Nakano, T., Goto, M.: An automatic singing skill evaluation method for unknown melodies using pitch interval accuracy and vibrato features. In: Proc. INTER- SPEECH (September 2006)Google Scholar