Hybrid solutions for the one-microphone speech enhancement problem

01 January 2019 → 31 December 2022
Regional and community funding: Special Research Fund
Research disciplines
  • Natural sciences
    • Natural language processing
  • Social sciences
    • Knowledge representation and machine learning
  • Engineering and technology
    • Antennas and propagation
    • Signal processing
    • Biomedical signal processing
    • Audio and speech computing
Speech enhancement noise suppression knowledge-based approaches machine learning statistical speech enhancement
Project description

Incorporating (hand-crafted) structured models into traditional speech enhancement approaches gives an improvement, albeit constrained by the model's limitations. Alternatively, employing deep neural networks (DNNs) leads to better performance for conditions seen during training. However,
these methods generalise poorly. We propose to systematically incorporate structured knowledge into DNNs, thereby combining significantly improved speech enhancement with greater robustness to unseen conditions.