ACL2025
Live Football Commentary System Providing Background Information
Yuichiro Mori, Chikara Tanaka, Aru Maekawa, Satoshi Kosugi, Tatsuya Ishigaki, Kotaro Funakoshi, Hiroya Takamura, Manabu Okumura
1 citation
Abstract
Previous research on sports commentary generation has primarily focused on describing major events in the match. However, real-world commentary often includes comments beyond what is visible in the video content, e.g., "Florentina has acquired him for 7 million euros." For enhancing the viewing experience with such background information, we developed an audio commentary system for football matches that generates utterances for the background information, as well as play-by-play commentary. Our system first extracts visual scene information and determines whether it is an appropriate timing to produce an utterance. Then, it decides which type of utterance to generate: play-byplay or background information. In the latter case, the system leverages external knowledge through retrieval-augmented generation.