School of Computer Science and Statistics
Restoring speech communication in individuals that can’t speak or have difficulty speaking (e.g., individuals with ALS) is an important challenge that could benefit many. While many solutions have been proposed that have various limitations, recent progress in machine learning methods (e.g., transformers) open new opportunities. This project aims to decode the intended speech of individuals … Read more
When designing and training a neural network model the hyperparameters include the SGD step size, mini-batch size, gradient decay policy, choice of regularisation etc. Selecting values for these hyperparameters is a key step in obtaining a useful model. While selection is commonly based on heuristics and trial and error, there is also much interest in … Read more
Auditory communication has a central role in our society. However, it remains unclear how our brains allow us to understand complex sounds, such as speech and music. The use of machine learning methods to study neural data has recently led to a major paradigm shift, greatly advancing our understanding of auditory perception. The Di Liberto … Read more