Human VOICE
Human voice research encompasses the study of voice production, perception, and application, aiming to understand and manipulate vocal characteristics for various purposes. Current research focuses on improving voice conversion techniques (e.g., using diffusion models and k-nearest neighbors approaches), developing more robust and efficient speech synthesis models (including those for unseen speakers and diverse languages), and addressing ethical concerns surrounding AI-generated voices and potential biases in speech recognition systems. This field has significant implications for diverse applications, including assistive technologies, personalized voice assistants, improved accessibility for individuals with speech impairments, and the development of more equitable and trustworthy AI systems.
Papers
Walk along: An Experiment on Controlling the Mobile Robot 'Spot' with Voice and Gestures
Renchi Zhang, Jesse van der Linden, Dimitra Dodou, Harleigh Seyffert, Yke Bauke Eisma, Joost C. F. de Winter
Cluster and Separate: a GNN Approach to Voice and Staff Prediction for Score Engraving
Francesco Foscarin, Emmanouil Karystinaios, Eita Nakamura, Gerhard Widmer