Email: portico-services@ucl.ac.uk
Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
- Lecturer
- Speech, Hearing & Phonetic Sciences
- Div of Psychology & Lang Sciences
- Faculty of Brain Sciences
I work actively in standardisation committees to bring research to application, and my work (and name) was incorporated in the international standard ISO 532-3. I have consulted several companies in the last few years, for example I was among the first experts in Uber's Elevate programme and advised on quiet eVTOLs.
My research follows two related branches, computational models and perception of speech and hearing. While some of my research targets basic neuroscience and helps improving our understanding of the human brain using behavioural methods and imaging, other parts of my research are more applied and help diagnosing and compensating for a hearing loss, design quiet environments, better speech understanding and improving speech machine learning.
My research activities span:
Computational and Technology:
- Bayesian active learning
- Automatic speech recognition and text-to-speech
- Loudness modelling
- Signal processing and forecasting
- Machine learning applied to speech and hearing
Perception:
- Perception in background noise
- Loudness
- Psychoacoustics
- Human phoneme recognition
- Irrelevant Speech Effect: Features of speech
I teach PALS0039 Introduction to Deep Learning for Speech and Language Processing and PALS0051 Advanced speech data processing in R (from 2024).
I am open to supervise MSc and PhD dissertations about Speech Technology, Auditory Perception, Hearing, Speech ML, Bayesian ML and any other of my research interests.
If you are a very good student and want to do your PhD with me, please get in contact early to explore possible funding routes. I will advertise already available funding and open post-doc opportunities on my Twitter.