Toshiba Fellowship Programme

MultiMedia Research Topics

Emotional speech synthesis

The aim of this research is to provide expressive or emotional features to synthetic speech. The research project will include creating emotion models where prosody and synthesis parameters are defined with regard to emotion, and developing prosody generation models for emotional speech.

Candidates should possess expertise on speech synthesis, statistical machine learning and C, C++ programming skills.

Machine vision for human behaviour understanding

This project is concerned with developing a novel method of human behaviour understanding in intelligent surveillance, aiming in particular at intent recognition, anomaly detection and danger prediction. The approach should employ a combination of computer vision and machine learning technologies. This project covers the theoretical framework and fundamental experiments in understanding human behaviour and the surrounding real 3D world.

Candidates are required to possess expertise in computer vision and/or machine learning together with programming skills sufficient to formulate experiments. Having an interest in behavioural science is preferred.