Submission
The submission is required to consist of one ZIP file that contains all of the following items.
- Prediction score result for each audio–text pair (csv)
-
You must write [wavfilename, prediction score] on a line for each audio-text pair in the test dataset, and save them all in a single csv file.
-
If you are submitting multiple systems, you must create and submit a separate CSV file for each system.
- System description with pre-defined format (yaml)
-
If you are submitting multiple systems, you must create and submit a separate system description file for each system.
-
Format: ※ The YAML template will open on November 18 [AoE].
- Technical report (pdf) (Optional, but strongly recommended)
- The technical report should be two pages or more.
- Format: Under preparation
※ The submission link will open on November 18 (AoE).
The Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.