WGansing: a multi-voice singing voice synthesizer based on the Wasserstein-Gan

Citació

  • Chandna P, Blaauw M, Bonada J, Gómez E. WGansing: a multi-voice singing voice synthesizer based on the Wasserstein-Gan. In: EUSIPCO 2019. 27th European Signal Processing Conference; 2019 Sep 2-6; A Coruña, Spain. New Jersey: IEEE; 2019. [5 p.]. DOI: 10.23919/EUSIPCO.2019.8903099

Enllaç permanent

Descripció

  • Resum

    We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder parameters for acoustic modelling, to separate the influence of pitch and timbre. This facilitates the modelling of the large variability of pitch in the singing voice. Our network takes a block of consecutive frame-wise linguistic and fundamental frequency features, along with global singer identity as input and outputs vocoder features, corresponding to the block of features. This block-wise approach, along with the training methodology allows us to model temporal dependencies within the features of the input block. For inference, sequential blocks are concatenated using an overlap-add procedure. We show that the performance of our model is competitive with regards to the state-of-the-art and the original sample using objective metrics and a subjective listening test. We also present examples of the synthesis on a supplementary website and the source code via GitHub.
  • Descripció

    Comunicació presentada al EUSIPCO 2019: 27th European Signal Processing Conference, celebrat del 2 al 6 de setembre de 2019 a La Corunya, Espanya.
  • Mostra el registre complet