Vocoder-free text-to-speech synthesis incorporating generative adversarial networks using low-/multi-frequency STFT amplitude spectra - researchr publication

researchr

You are not signed in
Sign in
Sign up

Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari. Vocoder-free text-to-speech synthesis incorporating generative adversarial networks using low-/multi-frequency STFT amplitude spectra. Computer Speech & Language, 58:347-363, 2019. [doi]

Abstract is missing.

runs on WebDSL