Professor Martin Russell BSc, PhD, FIMA, CMath, MIEEE

Professor Martin Russell

School of Computer Science
Professor of Information Engineering

Contact details

Address
School of Computer Science
University of Birmingham
Edgbaston
Birmingham
B15 2TT
UK

Martin Russell is Professor of Information Engineering in the School of Computer Science. He joined the University of Birmingham in 1998.  His research interests are in speech and language science and technology. He has published over 150 research papers in these areas.

Qualifications

• PhD Mathematics, 1981
• BSc Mathematics, 1977

Biography

Martin Russell graduated from Hull University with a BSc (1977) and PhD (1981), both in mathematics. In 1980 he joined the newly formed Automatic Speech Recognition research group at the Royal Signals and Radar Establishment (RSRE Malvern). Later this became the DERA Speech Research Unit (SRU), the main government funded speech technology laboratory in the UK. He joined the School of Electronic and Electrical Engineering at the University of Birmingham in 1998 and moved to the School of Computer Science in 2018. Martin’s research is in the area of speech and language science and technology. He is particularly interested in the developments of new formalisms for speech pattern modelling, speech technologies for education and children, and the role of regional accents in speech and language technology. Martin’s research has been funded by EPSRC, the EU, UK Government and Industry, and the US Government.

Teaching

Teaching 2019/20

• Mathematical Modelling and Decision Making (UG Year 2)

• Intelligent Data Analysis (UG Year 3 and MSc)

Postgraduate supervision

Current PhD students are:

  • Xizi Wei: Automatic assessment of Motivational Interviews using Speech and Language technology
  • Mengjie Qian: Computer Assisted Language Learning for Children
  • Yikai Peng: Compensating for Object Variability in Object-Centered Human Activity Recognition
  • Guy Coop: Automatic Sentiment Analysis in Motivational Interview Conversations
  • Chloe Seivwright: Speech Recognition using Continuous State Hidden Markov Models

Research

RESEARCH THEMES
I am interested in all aspects of speech and language science and technology, and in particular automatic speech recognition. For many years I have worked on the development of novel mathematical acoustic speech models for speech recognition. I believe that an important challenge is to build computationally useful models of speech and language that capture its structure and regularities, to understand the underlying mechanisms that give rise to variability, and to understand the representations of speech and language that emerge in modern approaches based on deep neural networks and machine learning. I have an ongoing interest in speech and language technologies for children's speech, in the application of these technologies in education, and in the challenges of accommodating regional dialects and accents. I have also worked on the application of techniques originating in speech technology to other problems, for example human activity recognition.

Other activities

• Fellow of the Institute of Mathematics and its Applications (IMA)

• Member of the IEEE

• Member of ISCA (International Speech Communication Association)

• Co-founder and Chair (2012-2015) of the ISCA Special Interest Group SLaTE (Speech and Language Technologies in Education)

• Member of the Scientific Committee for WOCCI (Workshop on Child Computer Interaction)

• Member of the editorial boards of Computer Speech and Language and Natural Language Engineering

Publications

Recent publications

Article

Safavi, S, Russell, M & Jancovic, P 2018, 'Automatic Speaker, Age-group and Gender Identification from Children's Speech', Computer Speech and Language. https://doi.org/10.1016/j.csl.2018.01.001

Jean-Baptiste, E, Russell, M, Howe, J & Rotshtein, P 2017, 'Intelligent Prompting System to Assist Stroke Survivors', Journal of Ambient Intelligence and Smart Environments, vol. 9, no. 6, pp. 707-723. https://doi.org/10.3233/AIS-170461

Baber, C, Russell, M, Wing, A, Hermsdorfer, J & Khattab, A 2017, 'Creating Affording Situations: Coaching through Animate Objects', Sensors, vol. 17, no. 2308, 2308, pp. 1-17. https://doi.org/10.3390/s17102308

Jean-Baptiste, EMD, Rotshtein, P & Russell, M 2016, 'CogWatch: Automatic prompting system for stroke survivors during activities of daily living', Journal of Innovation in Digital Ecosystems, vol. 3, no. 2, pp. 45-56. https://doi.org/10.1016/j.jides.2016.10.003

Conference contribution

Peng, Y, Jancovic, P & Russell, M 2019, Compensating for object variability in DNN–HMM object-centered human activity recognition. in 2019 27th European Signal Processing Conference (EUSIPCO). Signal Processing Conference (EUSIPCO), European, IEEE Xplore, 27th European Signal Processing Conference, A Coruña, Spain, 2/09/19. https://doi.org/10.23919/EUSIPCO.2019.8903124

Qian, M, Jancovic, P & Russell, M 2019, The University of Birmingham 2019 Spoken CALL Shared Task Systems: Exploring the importance of word order in text processing. in 8th Workshop on Speech and Language Technology in Education. Graz, Austria.

Fringi, E & Russell, M 2018, Analysis of phone errors attributable to phonological effects associated with language acquisition through bottleneck feature visualisations. in Proceedings Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 2573-2577, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-2422

Bai, L, Weber, P, Jancovic, P & Russell, M 2018, Exploring how phone classification neural networks learn phonetic information by visualising and interpreting bottleneck features. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 1472-1476, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-2462

Baur, C, Caines, A, Chua, C, Gerlach, J, Qian, M, Rayner, M, Russell, M, Strik, H & Wei, X 2018, Overview of the 2018 spoken CALL shared task. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 2354-2358, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-97

Qian, M, Bai, L, Jancovic, P & Russell, M 2018, Phone recognition using a non-linear manifold with broad phone class dependent DNNs. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 3753-3757, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1376

Qian, M, Wei, X, Jancovic, P & Russell, M 2018, The University of Birmingham 2018 spoken CALL shared task systems. in Proceedings of Interspeech 2018. Interspeech, vol. 2018, ISCA, Hyderabad, India, pp. 2374-2378, Interspeech 2018, Hyderabad , India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1372

Baur, C, Chua, C, Gerlach, J, Rayner, M, Russell, M, Strik, H & Wei, X 2017, Overview of the 2017 Spoken CALL Shared Task. in O Engwall, J Lopes & I Leite (eds), Proceedings of the 7th ISCA Workshop on Speech and Language Technology in Education. Stockholm, Sweden.

Qian, M, Wei, X, Jancovic, P & Russell, M 2017, The University of Birmingham 2017 SLaTE CALL Shared Task Systems. in O Engwall, J Lopes & IL (eds), Proceedings of the 7th ISCA Workshop on Speech and Language Technology in Education. ISCA, Stockholm, Sweden.

Bai, L, Jancovic, P, Russell, M, Weber, P & Houghton, S 2017, Phone classification using a non-linear manifold with broad phone class dependent DNNs. in Proceedings of Interspeech 2017. Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1179

Fringi, E, Lehman, J & Russell, M 2016, The role of phonological processes and acoustic confusability in phone errors in children’s ASR. in Proceedings of Workshop on Child-Computer Interaction (WOCCI 2016)., 2, ISCA, pp. 10-15. https://doi.org/10.21437/WOCCI.2016-2

View all publications in research portal