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.

References:

• 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.

Presentation given at ACEMuP #5, 3-4 June 2021 (online)

Video presentation for virtual conference ICASSP2020

Ref: L. Ardaillon, A. Roebel, “GCI detection from raw speech using a fully-convolutional network”, Proc ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 6739–6743, 2020. arXiv preprint