Measuring Time Delay Tolerance in Third-Person Live Commentary for Super Smash Bros. Ultimate

This study proposes a methodology for measuring the acceptable delay tolerance for third-person game commentary. Third-person game commentary refers to commentary delivered by someone other than the player, with the role of helping viewers better understand the game and enhancing the viewing experience. With the recent advancement of AI, there has been increasing interest in automating such commentary using video understanding and audio generation. However, automating this process using video understanding and audio generation introduces delays, potentially affecting the naturalness of the commentary. In this context, since the extent to which such delays are acceptable to viewers remains unclear, we address this issue. The tolerance is modeled using an unnormalized Gaussian function. Through experiments on Super Smash Bros. Ultimate with 727 participants, we found that the average acceptable delay for this game is 3.71 seconds, with variations depending on different viewer attributes and gameplay contexts.

• Publication year

  2025

• Venue

  2025 IEEE Conference on Games (CoG)

• Publication date

  2025-08-26

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/CoG64752.2025.11114300
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• MatchTime: Towards Automatic Soccer Game Commentary Generation

  2024cited by this paper
• Automated Cricket Commentary Generation for Videos

  2023cited by this paper
• Open-domain Video Commentary Generation

  2022cited by this paper
• Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech

  2021cited by this paper
• Generating Racing Game Commentary from Vision, Language, and Structured Data

  2021cited by this paper
• Learning to Prompt for Vision-Language Models

  2021cited by this paper
• VinVL: Revisiting Visual Representations in Vision-Language Models

  2021cited by this paper
• SMASH Corpus: A Spontaneous Speech Corpus Recording Third-person Audio Commentaries on Gameplay

  2020cited by this paper
• Negotiating quality assessment in media accessibility: the case of live subtitling

  2020cited by this paper
• Generating Live Soccer-Match Commentary from Play Data

  2019cited by this paper
• Quality assessment in interlingual live subtitling: The NTR Model

  2018cited by this paper
• Investigating the Role of Sports Commentary: An Analysis of Media-Consumption Behavior and Programmatic Quality and Satisfaction

  2016cited by this paper
• The Development of a Methodology to Evaluate the Perceived Quality of Live TV Subtitles

  2013cited by this paper
• Sensorimotor synchronization: A review of the tapping literature

  2005cited by this paper
• The processing-speed theory of adult age differences in cognition.

  1996cited by this paper
• The method of constant stimuli is inefficient

  1990cited by this paper
• Review of text-to-speech conversion for English.

  1987cited by this paper
• Shortest connection networks and some generalizations

  1957cited by this paper

• No citing papers are available for this paper.