Project Details
Abstract
The project focuses on designing audio understanding models for spoken language and natural human-machine interaction. Methods include audio representation aided by external knowledg to support applications, including dialogue, spoken language learning, and detection of atypical spoken phenomena.
Submitting Institute Name
Hamad Bin Khalifa University (HBKU)
| Sponsor's Award Number | QCRI-CORE-000011 |
|---|---|
| Proposal ID | QCRI-CORE-000011 |
| Status | Active |
| Effective start/end date | 1/07/24 → 1/06/26 |
Primary Theme
- Artificial Intelligence
Primary Subtheme
- AI - Education
Secondary Theme
- Artificial Intelligence
Secondary Subtheme
- AI - Healthcare
Keywords
- audio LLM
- Speech technology
- Representation learning
Fingerprint
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.