About
Research & Development
Enhancing Speech Recognition for Dysarthria Through Multi-Speaker Learning
TLDR: The paper introduces a "Cross-Speaker Joint Fine-Tuning" strategy for dysarthric speech recognition using the Chinese Dysarthria Speech Database (CDSD). It challenges conventional speaker-specific...
Research & Development
Rethinking How We Interact with AI: Insights from a Design Thinking Workshop on LLM Interfaces
TLDR: This research paper details insights from a design thinking workshop held at the deRSE25 conference, focusing on developing innovative user interface (UI) concepts...
Research & Development
Interpretable AI for Safer Autonomous Driving
TLDR: The research introduces DTCP, a method that enhances the interpretability of end-to-end autonomous driving systems by using novel diversity loss functions. This approach...
Research & Development
Enhancing AI Uncertainty Estimates with Distance-Preserving Neural Processes
TLDR: Distance-informed Neural Process (DNP) is a new variant of Neural Processes that improves uncertainty estimation and out-of-distribution detection. It achieves this by combining...
Research & Development
Ensuring Robot Reliability: A New Framework for Error-Free LLM-Generated Control Programs
TLDR: NRTrans is a new framework that translates natural language into robot control programs with correctness guarantees. It uses a simplified Robot Skill Language...
Research & Development
Enhancing Text Line Detection in Historical Manuscripts with Limited Data
TLDR: Researchers developed a new method for text line segmentation in historical documents that works exceptionally well with very little training data. They used...