Speech Science and Technology

The major themes of our current research are:

  • Applied research in speech signal processing and speech signal classification
  • Computational modelling of articulation and acquisition mechanisms
  • Computational modellling of auditory perception
  • Machine learning for speech and hearing

 

Key researchers:

My research involves many aspects of speech science and technology: speech production, hearing, speech perception, speech acquisition, speech synthesis, speech recognition and speaker recognition.

Recent research activities include:
Centre for Law-Enforcement Audio Research (CLEAR). A joint research centre with Imperial College London that investigates methods for the enhancement of degraded speech signals.

Avatar Therapy. A project that investigates the use of computer avatars in the provision of therapy for sufferers of auditory hallucinations (hearing voices).

KLAIR Virtual Infant. A machine learning toolkit for the study of the computational modelling of early speech acquisition by infants through real-time interaction with caregivers.

VOQAL Voice Quality Toolbox. A toolkit for the analysis of changes in voice quality caused by aging, disease or stress.

Meet the researcher:

 

Computational modellling of auditory perception

My research is primarily concerned with the basic mechanisms of speech production and perception in connected discourse in general, and speech prosody in particular. My work also concerns computational modeling and automatic synthesis of speech, computational modeling of the neural process of speech acquisition and emotions in speech.

I'm interested in auditory perception and computational models of the underlying neuroscientific mechanisms and for applied, realistic scenarios. With speech being the most important sound for humans, the biggest part of my research revolves around speech perception. I use and develop deep learning and other machine learning methods to help answer my research questions, as part of computational models and for new applications in the field.

Researchers at UCL: Julian Leff (Emeritus Professor, UCL Mental Health Sciences), Mark Huckvale and Geoff Williams. In collaboration with Thomas Jamieson-Craig, Philippa Garety and Paul McCrone, Institute of Psychiatry.

Wellcome Trust Strategic Translation Award. Duration 5 years: August 2012- mid 2017

About 25% of people with schizophrenia continue to suffer with persecutory auditory hallucinations despite drug treatment. Their capacity to work and make relationships is grossly impaired, often for the rest of their life. We have developed and evaluated a novel therapy based on computer technology which enables each patient to create an avatar of the entity (human or non-human) that they believe is talking to them. The therapist promotes a dialogue between the patient and the avatar in which the avatar progressively comes under the patient’s control. The project will refine the system, streamline the technology to make it more user-friendly and evaluate the system by a randomised controlled trial conducted by an independent team of researchers.

The VULCAN project is a new feasibility study funded by the European Space Agency under the Artes 20 programme. The project partners are UCL Speech, Hearing and Phonetic Sciences, UCL Mullard Space Sciences Laboratory Centre for Space Medicine and the Institute for Biomedical Problems (IBMP) in Moscow, Russia. It will run from January 2016 to January 2017.