Professor Guy J Brown

Department of Computer Science
University of Sheffield

RESEARCH |  PUBLICATIONS |  PROJECTS |  RESOURCES |  PHD STUDENTS |  TEACHING |  CONTACT


RESEARCH

My main research interest is Computational Auditory Scene Analysis (CASA), which aims to build machine systems that mimic the ability of human listeners to segregate complex mixtures of sound. I also have interests in reverberation-robust automatic speech recognition, hearing impairment and music technology.

The following book gives an overview of CASA:

DeLiang Wang and Guy J. Brown (editors), Computational auditory scene analysis: Principles, Algorithms, and Applications. IEEE Press/Wiley-Interscience, 2006

The whole book is available online, if you are a subscriber to IEEE Xplore. Code examples from the book can be accessed here.


PUBLICATIONS

A reasonably complete list of publications is available via at orcid.org/0000-0001-8565-5476

Some publications are available online via the White Rose Archive

Selected recent publications:

H. Romero, N. Ma, G. J. Brown and E.A. Hill (2022) Acoustic screening for obstructive sleep apnoea in home environments based on deep neural networks. IEEE Journal of Biomedical and Health Informatics.
[IEEE Xplore]

H. Romero, N. Ma and G. J. Brown (2020) Snorer diarisation based on deep neural network embeddings. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2020), 4-8 May 2020, pp. 876-880.
[IEEE Xplore]

B. Wells, A. V. Beeston, E. Bradley, G. J. Brown, H. Crook and E. Kurtic (2019) Talking in time: The development of a self-administered conversation analysis based training programme for cochlear implant users. Cochear Implants International, published online 24th June 2019.
[Taylor & Francis Online]

P. Vecchiotti, N. Ma, S. Squartini and G. J. Brown (2019) End-to-end binaural sound localisation from the raw waveform. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2019), 12-17 May 2019, pp. 451-455.
[IEEE Xplore][arXiv]

H. E. Romero, N. Ma, G. J. Brown, A. V. Beeston and M. Hasan (2019) Deep learning features for robust detection of acoustic events in sleep-disordered breathing. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP-2019), 12-17 May 2019, pp. 810-814.
[IEEE Xplore][arXiv]

N. Alghamdi, S. Maddock, R. Marxer, J. Barker and G. J. Brown (2018) A corpus of audio-visual Lombard speech with frontal and profile views. Journal of the Acoustical Society of America, 143 (6), pp. 523-529.
[PDF] [Corpus download] [White Rose Online] Copyright (2018) Acoustical Society of America. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America. The article appeared in J. Acoust. Soc. Am. 143 (6), 523 (2018) and may be found at https://doi.org/10.1121/1.5042758.

N. Ma, J. A. Gonzalez and G. J. Brown (2018) Robust binaural localization of a target sound source by combining spectral source models and deep neural networks. IEEE Transactions on Audio, Speech and Language Processing, 26 (11), pp. 2122-2131.
[IEEE Xplore] [White Rose Archive]

N. Ma, T. May and G. J. Brown (2017) Exploiting deep neural networks and head movements for robust binaural localisation of multiple sources in reverberant environments. IEEE Transactions on Audio, Speech, and Language Processing, 25 (12), pp. 2444-2453.
[IEEE Xplore] [White Rose Archive]

N. Alghamdi, S. Maddock, J. Barker and G. J. Brown (2017) The impact of automatic exaggeration of the visual articulatory features of a talker on the intelligibility of spectrally distorted speech. Speech Communication, 95, pp. 127-136.
[ScienceDirect] [White Rose Archive]

R. W. Mill and G. J. Brown (2016) Utilising temporal signal features in adverse noise conditions: Detection, estimation, and the reassigned spectrogram. Journal of the Acoustical Society of America, 139, pp. 904-917.
[PDF] [Matlab code] [White Rose Archive] Copyright (2016) Acoustical Society of America. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America. The article appeared in J. Acoust. Soc. Am. 139, 904 (2016) and may be found at http://dx.doi.org/10.1121/1.4941566.

U. Remes, A. Ramirez Lopez, L. Juvela, K. Palomäki, G. J. Brown, P. Alku, M. Kurimo (2016) Comparing human and automatic speech recognition in a perceptual restoration experiment. Computer Speech and Language, 35, pp. 14-31.
[White Rose Archive] [ScienceDirect]

N. Ma, R. Marxer, J. Barker and G. J. Brown (2015) Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), pp. 490-495.
[IEEE Xplore]

T. May, N. Ma and G. J. Brown (2015) Robust localisation of multiple speakers exploiting head movements and multi-conditional training of binaural cues. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2679-2683.
[White Rose Archive] [IEEE Xplore]

N. Ma, T. May, H. Wierstorf and G. J. Brown (2015) A machine-hearing system exploiting head movements for binaural sound localisation in reverberant conditions. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2699-2703.
[IEEE Xplore]

S. Keronen, H. Kallasjoki, K. J. Palomäki, G. J. Brown and J. F. Gemmeke (2015) Feature enhancement of reverberant speech by distribution matching and non-negative matrix factorization. EURASIP Journal on Advances in Signal Processing, 76, pp. 1-14.
[White Rose Archive] [SpringerOpen]

A. V. Beeston, G. J. Brown and A. J. Watkins (2014) Perceptual compensation for the effects of reverberation on consonant identification: Evidence from studies with monaural stimuli. Journal of the Acoustical Society of America, 136 (6), pp. 3072-3084.
[PDF] [White Rose Archive] [AIP Scitation] Copyright (2014) Acoustical Society of America. This article may be downloaded for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America. The article appeared in J. Acoust. Soc. Am. 136, 3072 (2014) and may be found at http://dx.doi.org/10.1121/1.4900596.

T. Jürgens, T. Brand, N. Clark, R. Meddis and G. J. Brown (2013) The robustness of speech representations obtained from simulated auditory nerve fibers under different noise conditions. Journal of the Acoustical Society of America, 134 (3), EL282-288.
[AIP Scitation (full text)]

E. Kurtic, G. J. Brown and B. Wells (2013) Resources for turn competition in overlapping talk. Speech Communication, 55, pp. 721-743.
[ScienceDirect]

S. Keronen, H. Kallasjoki, U. Remes, G. J. Brown, J. F. Gemmeke and K. J. Palomäki (2013) Mask estimation and imputation methods for missing data speech recognition in a multisource reverberant environments. Computer Speech and Language, 27 (3), pp. 798-819.
[ScienceDirect]

N. R. Clark, G. J. Brown, T. Jürgens and R. Meddis (2012) A frequency-selective feedback model of auditory efferent suppression and its implications for the recognition of speech in noise. Journal of the Acoustical Society of America, 132, 1535.
[AIP Scitation]

J. Gorisch, B. Wells and G. J. Brown (2012) Pitch contour matching and interactional alignment across turns: An acoustic investigation. Language and Speech, 55 (1), pp. 57-76.
[SAGE Journals]

K. J. Palomäki and G. J. Brown (2011) A computational model of binaural speech recognition: role of across-frequency vs. within-frequency processing and internal noise. Speech Communication 53, pp. 924-940.
[ScienceDirect]

G. J. Brown, R. F. Ferry and R. Meddis (2010) A computer model of auditory efferent suppression: Implications for the coding of speech in noise. Journal of the Acoustical Society of America, 127(2), pp. 943-954.
[AIP Scitation]

[Back to top]


PROJECTS

Two funded research projects are current:

  • BRAHMS - Breathing Restriction Assessment via Home Monitoring of Sleep. Innovate UK.
  • I am working with a Sheffield rock band on a project involving music and AI.

Recently completed projects:

[Back to top]


RESOURCES

[Back to top]


PHD STUDENTS AND ALUMNI

Current PhD students:

  • Dimitris Pappas - emergent distributed systems for computational auditory scene analysis (with George Eleftherakis, CITY College/International Faculty of the University of Sheffield)
  • Alex Stamatiadis - quantification of aesthetic properties of music (with Renee Timmers, Department of Music)

Previous PhD students:

  • Hector Romero (Passion for Life Healthcare)
  • Thomas White
  • Ryan Kirkbride
  • Najwa Alghamdi (King Saud University)
  • Tim Metcalfe (Aucoda)
  • Amy Beeston (Department of Computer Science, University of Sheffield)
  • Jana Eggink (BBC)
  • Matthew Robertson (BAE Systems Detica)
  • Darryl Godsmark (Intuitive Systems Ltd)
  • Jan Gorisch (Laboratoire Parole et Langage, Aix-en-Provence)
  • Brian L. Karlsen (Terma Aerospace, Denmark)
  • Emina Kurtic (Department of Human Communication Sciences, University of Sheffield)
  • Simon Makin (Self-employed scientific writer)
  • Robert Mill (Spiral Software, Cambridge)
  • Simon Tucker (Google, California)
  • Stuart Wrigley (Department of Computer Science, University of Sheffield)

[Back to top]


TEACHING

I am teaching COM6655 Professional Issues in the current (2021-22) session. Course materials are available through Blackboard.

[Back to top]


CONTACT

Professor Guy J Brown
Department of Computer Science
University of Sheffield
Regent Court
211 Portobello
Sheffield S1 4DP
United Kingdom

Tel: +44 (0)114 222 1821
Fax: +44 (0)114 222 1810

Email: g.j.brown@sheffield.ac.uk