Recreation of the singing voice of the baroque singer Farinelli

Demonstration of the transposition of singing voice by means of the auto encoder/neural vocoder system developed in the ARS project, applied in the context of the artistic residency of Judith Deschamps.

Extract of the presentation « Quell’usignolo che innamorato », the resurgence of an artificial voice.


  • F. Bous, A. Roebel, “A Bottleneck Auto-Encoder for F0 Transformations on Speech and Singing Voice”. Information 2022, 13(3), 102; online version.
  • A. Roebel, F. Bous, “Neural Vocoding for Singing and Speaking Voices with the Multi-Band Excited WaveNet”. Information 2022, 13(3), 103; online version.