DSTC8

The DSTC8 dataset is used for addressing the audio visual scene-aware dialog task, specifically involving generating responses based on multimodal inputs including video, audio, and dialogue history.

Data and Resources

Cite this as

Hwanhee Lee, Seunghyun Yoon, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Kyomin Jung (2024). Dataset: DSTC8. https://doi.org/10.57702/jl5zi3te

DOI retrieved: November 25, 2024

Additional Info

Field Value
Created November 25, 2024
Last update November 25, 2024
Defined In https://doi.org/10.48550/arXiv.2004.08299
Version 1.0
Author Hwanhee Lee
More Authors
Seunghyun Yoon
Franck Dernoncourt
Doo Soon Kim
Trung Bui
Kyomin Jung