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

Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari

BibTeX
@article{saito2019vocoder,
  author = {Yuki Saito and Shinnosuke Takamichi and Hiroshi Saruwatari},
  title = {{Vocoder-free text-to-speech synthesis incorporating generative adversarial networks using low-/multi-frequency STFT amplitude spectra}},
  journal = {Comput. Speech Lang},
  year = {2019},
  doi = {10.1016/j.csl.2019.05.008},
}

Loading related content...

Figure