This is a project which is currently making use of HPC facilities at Newcastle University. It is active.
For further information about this project, please contact:
This project investigates generative AI methods for emotion-aware and personalised speech and dialogue systems using text and audio data.
The project uses Python with the PyTorch deep learning framework, CUDA-enabled GPU computing, and supporting scientific and speech-processing libraries. Compute workloads include GPU-accelerated neural network training, hyperparameter optimisation, speech synthesis, multimodal feature processing, ablation studies and large-scale model evaluation. Slurm batch jobs and job arrays will be used to manage repeated experiments efficiently.