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.

Authors: Yoshida, Yuri; Nisimura, Ryuichi; Irino, Toshio; Kawahara, Hideki
Affiliation: Wakayama University, Wakayama City, Japan
AES Conference: 35th International Conference: Audio for Games (February 2009)
Paper Number: 6
Publication Date: February 1, 2009
Subject: Audio for Games: Speech Processing and Analysis

Click to purchase paper as a non-member or you can login as an AES member to see more options.

No AES members have commented on this paper yet.

Subscribe to this discussion

To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.

Start a discussion!

If you would like to start a discussion about this paper and are an AES member then you can login here:
Username:
Password:

If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.