Research program 04
Language and Human Interfaces
Speech and language systems that support natural interaction with scientific and physical-intelligence systems, beginning with Twi, Ghanaian English and real-world code-switching.
Research programInternal
Research objective
Develop interfaces that can clarify uncertainty, recover from misunderstanding and preserve human expertise in field workflows.
01 / Core scientific questions
Questions under investigation.
- How should field systems handle tonal language and code-switching?
- How can a system detect misunderstanding before it affects a physical task?
- Which interaction patterns work when screens, literacy or connectivity are constrained?
02 / Current projects
Research topics.
- Low-resource speech recognition
- Natural text-to-speech
- Tonal-language modeling
- Code-switching
- Voice-directed field systems
- Clarification and misunderstanding detection
03 / Methods
Intended methods.
- Consent-based speech collection
- Pronunciation and lexicon development
- Human-in-the-loop transcription
- Task-oriented interface evaluation
04 / Evaluation
How the program will be evaluated.
- Recognition across speakers and environments
- Clarification behavior
- Task completion
- Human correction burden
Evaluation protocols and results will be published only after review. No performance result is claimed on this page.
05 / Research infrastructure
Systems and related models.
06 / Verification pending
Researchers and related publications.
Researchers involved
Verified researcher profiles have not yet been published.
Related publications
No public publication is currently associated with this program.