New survey maps 5 key dimensions for automated presentation coaching
Researchers categorize coaching systems with a 5D taxonomy and reveal major gaps.
Deep Dive
A survey of automated presentation coaching systems introduces a five-dimensional task taxonomy covering segmental pronunciation, lexical stress, suprasegmental prosody, pacing, and content faithfulness. It maps existing tools—from pronunciation tutors to Q&A practice systems—onto this framework, highlighting coverage gaps. Key challenges include scarce annotated data, accent-fair feedback, and real-time diagnostics.
Key Points
- Five-dimensional taxonomy: segmental pronunciation, lexical stress, suprasegmental prosody, pacing, content faithfulness
- Mapping existing systems reveals gaps in pacing and content faithfulness coaching
- Open challenges include lack of diverse annotated datasets and real-time feedback constraints
Why It Matters
A structured framework to guide development of fair, real-time AI presentation coaches for professionals.