Important dates
-
Sep 10, 2020: Registration open
-
Sep 30, 2020: Registration closed
-
Oct 1, 2020: Start of dataset creation
-
Oct 15, 2020: End of dataset creation
-
Oct 31, 2020: Training dataset and TTS API specification requirement released;
-
Nov 20, 2020: TTS API submission; Start of evaluation phase
-
Dec 7, 2020: End of evaluation phase
-
Dec 15, 2020: Technical report submission
-
Dec 18, 2020: Result announcement (workshop day)
The VLSP Text-To-Speech (TTS) Challenge 2020 has been designed for understanding and comparing research techniques in building Vietnamese corpus-based TTS synthesizers on the same data. The basic challenge is to take the released speech database, build a TTS system with a training voice from the data. The synthetic utterances for test sentences from each synthesizer will then be evaluated through listening tests.
Participants have to join to build the dataset before receiving it. The main task is to transcribe or to correct the transcription for a part of the dataset.
Training data
You will be provided the training dataset after participating in the dataset building. The duration of the dataset is about 5-6 hours of a single speaker.
Test data
You have to submit TTS API specification so that the organizer can use your API to synthesize utterances from text in the test set. You will receive your synthetic utterances when the evaluation phase ends. The synthesized utterances will be presented to three groups of listeners: speech experts, volunteers, and undergraduates.