Facilitating Development of Pragmatic Competence through a Voice-driven Video Learning Interface
summary
A web tool lets learners repeat lines from any YouTube or local video, uses general speech recognition to transcribe and translate utterances, and flags correctness when captions exist. A 27-participant lab study shows the speech-driven interface yields more lookups and a strong order effect (voice-first users nearly double interactions), and a field release attracts 131 participants with 71 users averaging ~70 phrases; voice recognition errors and mixed reactions to open-ended content limit results.
AI-written summary · about
chapters (13)
- 0:00Introduction to pragmatic competence
- 1:30Limitations of traditional learning
- 2:33Authentic video learning challenges
- 3:44Speech recognition approach
- 4:46Live demo of the interface
- 6:17Preliminary study design
- 8:04Study results and insights
- 9:49User feedback on cognitive load
- 10:31Limitations of voice recognition
- 11:35System deployment and features
- 12:59Field study outcomes
- 13:21Contributions and future work
- 14:22Q&A session begins
related talks
55mDigital Modernization Through Accessibility
24mFail fast, fail cheap, making voice apps the guerrilla way
23mDesigning for Accessibility
13mReMap: Lowering the Barrier to Help-Seeking with Multimodal Search
19mAlexa, show me a good voice UI
20mEmbracing the Voice Revolution
50mDesigning Experiences For Voice Interactions
17mCapture-Time Feedback for Recording Scripted Narration