INTERSPEECH 2022 Sample Data

• H. Tachibana, M. Inahara, M. Go, Y. Katayama, Y. Watanabe, Diffusion Generative Vocoder for Fullband Speech Synthesis Based on Weak Third-order SDE Solver, Submitted to INTERSPEECH 2022

VCTK Reconstruction Examples

• Input data are excerpted from the CSTR VCTK Corpus.
• Notes on the VCTK
  • The VCTK Corpus is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.

Bandwidth Extension (Speech Superresolution) Examples

• Input data are excerpted from the LibriSpeech ASR Corpus.
• Notes on the LibriSpeech Corpus
  • The LibriSpeech is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) License.
  • V. Panayotov et al. “LibriSpeech: An ASR Corpus based on Public Domain Audio Books,” Proc. ICASSP 2015.
  • Changes:
    • Each data was resampled from 16kHz to 48kHz.