The TTS test set will be released by March 8, 2018 at 8:30 am.
The test set is a text file containing 30 numbered sentences (provided via a web link) in the news domain, with information on dates, personal names, foreign location names etc. The participant can choose to generate speech in one or more dialects of the three regions: Northern, Southern and Central.
Result submission: The synthesized speech for each sentence (totally automatically generated) should be saved as a .wav file (16K, 16 bits) under the name format <team's name><sentence's number>.wav. Then all these 30 files should be compressed in a zip file named <team's name>.zip. The obtained zip file need to be uploaded via a web service (sent to participant together with the evaluation data) before 6:00 pm on March 9, 2018.
A technical report of each participant's system should be submitted before 6:00 pm on March 15, 2018.