The technique used for this composition is a semi automatic system for speech to chant conversion. The transformation is performed using an implementation of shapeinvariant signal modifications in the phase vocoder and a recent technique for envelope estimation that is denoted as True Envelope estimation. We first describe the compositional idea and give an overview of the preprocessing steps that were required to identify the parts of the speech signal that can be used to carry the singing voice. Furthermore we describe the envelope processing that was used to be able to continusously transform the orginal voice of the actor into different female singing voices. Index Terms: envelope estimation, speech transformation, chant synthesis.
|Lolita_voices4.wav (17 MB)||Extract of a short voices only part of the composition Lolita by Joshua Fineberg.|
|leavemealone_jf.wav||Example sound file of an original male voice that has been|
|letthemplay_jf.wav||Example sound file of an original male voice that has been used as the basis for the speech to chant transformation.|
Bibliographic reference. Roebel, Axel / Fineberg, Joshua (2007): "Speech to chant transformation with the phase vocoder", In INTERSPEECH-2007, 4007-4008.