Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Laugh at Your Own Pace: Basic Performance Evaluation of Language Learning Assistance by Adjustment of Video Playback Speeds Based on Laughter Detection

Naoto Nishida, Hinako Nozaki, Buntarou Shizuki

TL;DR

The paper addresses L2 learners' difficulty processing native-speed videos during Extensive Viewing. It introduces an automated playback-speed system that modulates speed based on laughter-detected comprehension signals from facial expressions, bounded by $0.6x$ to $1.0x$ and adjusted in $±0.1x$ steps. The authors validate laughter as a proxy for understanding and demonstrate notable gains in comprehension for learners with TOEIC scores under $700$, while also reducing mental workload and preserving usability. Overall, the approach broadens access to authentic video materials for low-proficiency L2 learners and offers a practical, low-friction tool for Extended Viewing practice.

Abstract

Among various methods to learn a second language (L2), such as listening and shadowing, Extensive Viewing involves learning L2 by watching many videos. However, it is difficult for many L2 learners to smoothly and effortlessly comprehend video contents made for native speakers at the original speed. Therefore, we developed a language learning assistance system that automatically adjusts the playback speed according to the learner's comprehension. Our system judges that learners understand the contents if they laugh at the punchlines of comedy dramas, and vice versa. Experimental results show that this system supports learners with relatively low L2 ability (under 700 in TOEIC Score in the experimental condition) to understand video contents. Our system can widen learners' possible options of native speakers' videos as Extensive Viewing material.

Laugh at Your Own Pace: Basic Performance Evaluation of Language Learning Assistance by Adjustment of Video Playback Speeds Based on Laughter Detection

TL;DR

The paper addresses L2 learners' difficulty processing native-speed videos during Extensive Viewing. It introduces an automated playback-speed system that modulates speed based on laughter-detected comprehension signals from facial expressions, bounded by to and adjusted in steps. The authors validate laughter as a proxy for understanding and demonstrate notable gains in comprehension for learners with TOEIC scores under , while also reducing mental workload and preserving usability. Overall, the approach broadens access to authentic video materials for low-proficiency L2 learners and offers a practical, low-friction tool for Extended Viewing practice.

Abstract

Among various methods to learn a second language (L2), such as listening and shadowing, Extensive Viewing involves learning L2 by watching many videos. However, it is difficult for many L2 learners to smoothly and effortlessly comprehend video contents made for native speakers at the original speed. Therefore, we developed a language learning assistance system that automatically adjusts the playback speed according to the learner's comprehension. Our system judges that learners understand the contents if they laugh at the punchlines of comedy dramas, and vice versa. Experimental results show that this system supports learners with relatively low L2 ability (under 700 in TOEIC Score in the experimental condition) to understand video contents. Our system can widen learners' possible options of native speakers' videos as Extensive Viewing material.

Paper Structure

This paper contains 9 sections, 1 figure.

Table of Contents

  1. Introduction
  2. Related Work
  3. Existing Computer-Assisted Language Learning Methods
  4. Relationship between Playback Speed and Learner Comprehension
  5. Reduction of Learners' Workload
  6. Apparatus for Extensive Viewing
  7. Implementation
  8. Experiment
  9. Discussion & Future Work

Figures (1)

  • Figure 1: Values of Action Units 14 (AU14) of the 5 participants according to frame number. Red points represents the case when learners understand the contents. Blue points represents the case when they do not understand. Yellow ranges are punchline scenes in the experimental video. In the preliminary study, participants watched the video twice. First, they watched it normally; second, while watching they classified when they can keep up with the story and when they cannot.