Patrick D. Jenkins
Papers
1
Total Citations
6
H-Index
1
About
Patrick D. Jenkins is a researcher at the forefront of grounded language learning, a field that bridges natural language processing, computer vision, and signal processing. His work focuses on enabling machines to connect spoken language with physical, visual environments—a critical challenge for robotics and human-computer interaction. Jenkins is best known for his contributions to speech-based grounded language acquisition, where he addresses the compounded difficulties of sample efficiency and real-world deployment constraints. His most cited work, "A Spoken Language Dataset of Descriptions for Speech-Based Grounded Language Learning" (2021, 6 citations), introduced a pioneering multimodal dataset combining RGB and depth data with spoken descriptions. This resource has become a foundational tool for researchers exploring how agents can learn language directly from speech and visual input, rather than relying on text. By tackling the unique challenges of audio-visual grounding, Jenkins is helping to shape the next generation of interactive AI systems that can understand and act upon spoken instructions in physical spaces.
Research Focus
Key Achievements
Top Papers
- 1