ZeroSpeech 2019: TTS without T


The datasets for the ZeroSpeech Challenge 2019 are provided here for download.

Development dataset

  • Training dataset (English): english.tgz (2.5G, md5sum: 74e1debbfd2dd8d933fb2e4316a34a59)

  • Toy dataset (subset of the training dataset): english_small.tgz (156M, md5sum: 6bc157ebbcc94ab3bbcb960e6b089dc6)

Surprise dataset

  • Test dataset: (1.5G, md5sum: 7d48828a055d4b50d39c28529377d54b) This archive is protected by a password, please read and accept the following agreement to get the password.