Speech processing and enhancement techniques have evolved rapidly over the past decades, fuelled by advances in machine learning, neural network architectures, and signal processing methodologies.

Postdoctorate Viet Anh Trinh led a project within Strand 1 to develop a novel neural network architecture that can both recognize and generate speech. He has since moved on from iSAT to a role at ...

Hearing is so effortless for most of us that it’s often difficult to comprehend how much information the brain’s auditory system needs to process and disentangle. It has to take incoming sounds and ...