Biologically Inspired Deep Learning for Speech Information Processing

Primary supervisor

Additional information

Contact admissions office

Other projects with the same supervisor


  • Competition Funded Project (Students Worldwide)
This research project is one of a number of projects at this institution. It is in competition for funding with one or more of these projects. Usually the project which receives the best applicant will be awarded the funding. Applications for this project are welcome from suitably qualified candidates worldwide. Funding may only be available to a limited set of nationalities and you should read the full department and project details for further information.

Project description

Deep learning is a machine learning methodology via using hierarchical architectures of many layers to learn abstractive yet informative representations from raw data. While deep learning has turned out to be successful in tackling with many AI problems including speech information processing, it has been long criticised by neuroscientists as incompatible with current knowledge of neurobiology. On the other hand, a class of biologically inspired deep architectures have shown their superiority in some very challenging problems, e.g., in computer vision, deep convolutional neural networks (inspired by visual cortex structure) become dominated techniques in object recognition. While the convolutional neural networks have been attempted to facilitate speech recognition, there is a lack of proper biologically plausible deep architectures for speech information processing in general.

The project is going to investigate and develop novel biologically inspired deep neural architectures and learning algorithms especially for speech information processing. In this project, main issues to be studied include building blocks and learning algorithm inspired by speech analysis in auditory system, strategies of establishing deep neural architectures reflecting speech information processing in auditory system and other relevant issues, e.g., specific aspects on various speech information processing tasks in terms of real applications. In general, this project is suitable for one who is interested in fundamental research in machine learning and speech information processing while it is acceptable for one who has a relevant application problem in mind and wishes to tackle their problems with an emerging technology such as deep learning.

It is worth highlighting that this is an extremely challenging project of a great novelty. In order take this project, speech signal processing related research experience is required and it is also essential to be self-motivated and to have decent background knowledge in auditory systems, mathematics, machine learning as well as good programming skills. If you are interested in this project, please first visit my research student page: for the required materials and information prior to contacting me.

▲ Up to the top