Comprehensive Integration of Linguistic Features in a Human Inspired Speech Recognition Architecture

01 October 2016 → Ongoing
Regional and community funding: Special Research Fund
Research disciplines
  • Natural sciences
    • Artificial intelligence
  • Social sciences
    • Cognitive science and intelligent systems
Speech Recognition
Project description

In this project, a novel speech recognition framework and a set of accompanying, contemporary linguistic models is co-developed. The envisioned layered architecture combines local inference with inter-layer message passing, similar to what is believed to underlay human speech recognition. By facilitating the incorporation of knowledge (linguistic or other), such architecture is better equipped to model the complex inter-dependencies in speech.