Technical Program

Paper Detail

Presentation #1
Session:Voice Conversion and TTS
Location:Kallirhoe Hall
Session Time:Friday, December 21, 10:00 - 12:00
Presentation Time:Friday, December 21, 10:00 - 12:00
Presentation: Poster
Topic: Speech recognition and synthesis:
Paper Title: StarGAN-VC: Non-parallel many-to-many voice conversion using star generative adversarial networks
Authors: Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, NTT Corporation, Japan
Abstract: This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called StarGAN. Our method, which we call StarGAN-VC, is noteworthy in that it (1) requires no parallel utterances, transcriptions, or time alignment procedures for speech generator training, (2) simultaneously learns many-to-many mappings across different attribute domains using a single generator network, (3) is able to generate converted speech signals quickly enough to allow real-time implementations and (4) requires only several minutes of training examples to generate reasonably realistic sounding speech. Subjective evaluation experiments on a non-parallel many-to-many speaker identity conversion task revealed that the proposed method obtained higher sound quality and speaker similarity than a state-of-the-art method based on variational autoencoding GANs.