Gerard Roma has short brown hair, black rimmed glasses and is wearing a green top.

Dr Gerard Roma

Lecturer in Audio Software Engineering
School of Computing and Engineering
gerard.roma@uwl.ac.uk

Gerard Roma has extensive experience in research and development in the field of sound and music computing. He is also a practitioner in electronic and computer music. His research interests include audio analysis and synthesis, digital musical instruments, intelligent audio processing, audio source separation and environmental sound recognition.

  • Qualifications

    • BA (Universitat Autònoma de Barcelona)
    • MSc (Universitat Pompeu Fabra)
    • PhD (Universitat Pompeu Fabra) 

  • Memberships

    Audio Engineering Society

Research

  • Research and publications

    Book Chapters 

    FONT, F., ROMA., G. and SERRA, X. (2018). Sound Sharing and Retrieval. VIRTANEN, T., PLUMBLEY, M., and ELLIS, D., eds. Computational Analysis of Sound Scenes and Events. Springer, 2018, pp. 279-301. 

    ROMA, G. and HERRERA P. (2013).  Representing Music as Work in Progress. STEYN, J., ed. Structuring Music through Markup Language: Designs and Architectures. IGI Global, 2013, pp. 119-134.

    Journal Articles

    TREMBLAY, P.A. ,  ROMA, G., GREEN, O., (2022). The Fluid Corpus Manipulation Toolkit: enabling programmatic data mining as musicking. Computer Music Journal .45(2), pp. 9-23. 

    ROMA, G., XAMBÓ, A., GREEN, O. And TREMBLAY, P. A., (2021). A General Framework for Visualization of Sound Collections in Musical Interfaces.  Applied Sciences, 2021, 11 (24) (online)  

    ROMA, G., XAMBÓ, A. and FREEMAN, J. (2018). User-independent Accelerometer Gesture Recognition for Participatory Mobile Music. Journal of the Audio Engineering Society (JAES) .66 (6), pp .430-438. 

    XAMBÓ, A., ROMA, G., SHAH, P., TSUCHIYA, T., FREEMAN, J. and MAGERKO, B. (2018). Turn-taking and online chatting in Co-located and remote collaborative music live coding. Journal of the Audio Engineering Society (JAES) .66 (4), pp. 253-266. 

    ROMA, G.,  HERRERA, P. and NOGUEIRA W. (2017) Environmental sound recognition using short-time feature aggregation. Journal of Intelligent Information Systems (JIIS), 2017 (online). 

    GRAIS, E., ROMA, G., SIMPSON, A. and PLUMBLEY, M. (2017). Two-stage single-channel audio source separation using deep neural networks. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP) 25 (9), pp. 773-1783. 

    ROMA, G., ZANIN M., HERRERA P., TORAL S. L., FONT F. and SERRA X. (2012).  Small world networks and creativity in audio clip sharing. International Journal of Social Network Mining (IJSNM), 2012, 1(1), pp. 112 - 127. 

    ROMA, G., JANER J., KERSTEN S., SCHIROSA M., HERRERA P. and SERRA X. (2010).  Ecological acoustics perspective for content-based retrieval of environmental sounds. EURASIP Journal on Audio, Speech, and Music Processing, 2010 (online). 

    JANER, J., FINNEY N., ROMA G., KERSTEN S. and SERRA X. (2009).  Supporting soundscape design in virtual environments with content-based audio retrieval. Journal of Virtual Worlds Research, 2009, 2(3) (online). 

    Conference Papers (since 2018)

    ROMA, G., (2022). Comparing approaches for new AudioWorklets. Proceedings of the 7th Web Audio Conference (WAC). 

    TREMBLAY, P.A. ,  ROMA, G., GREEN, O., (2021). Digging it: Programmatic Data Mining as Musicking. Proceedings of the 2021 International Computer Music Conference (ICMC). 

    ROMA, G., GREEN, O. and TREMBLAY, P.A. (2021) Graph-based audio looping and granulation. Proceedings of the 24th International Conference on Digital Audio Effects (DAFx-21). 

    ROMA, G., GREEN, O. and TREMBLAY, P.A. (2020) Audio morphing using matrix decomposition and optimal transport. Proceedings of the 23rd International Conference on Digital Audio Effects (DAFx-20). 

    XAMBÓ, A., and ROMA, G. (2020) Performing Audiences: Composition Strategies for Network Music using Mobile Phones. Proceedings of the 20th International Conference on New Interfaces for Musical Expression (NIME). 

    ROMA, G., GREEN, O. and TREMBLAY, P.A. (2019) Time scale modification of audio using non-negative matrix factorization. Proceedings of the 22nd International Conference on Digital Audio Effects (DAFx-19). 

    ROMA, G., GREEN, O. and TREMBLAY, P.A. (2019). Adaptive mapping of sound collections for data-driven musical interfaces. Proceedings of the 19th International Conference on New Interfaces for Musical Expression (NIME). 

    TREMBLAY, P.A. ,  GREEN, O., ROMA, G.,  HARKER, A., (2019). From collections to corpora: exploring sounds through fluid decomposition. Proceedings of the 45th International Computer Music Conference (ICMC). 

    ROMA, G., GREEN, O. and TREMBLAY, P.A. (2018). Stationary / transient separation using convolutional autoencoders. Proceedings of the 21st International Conference on Digital Audio Effects (DAFX). 

    ROMA, G., GREEN, O. and TREMBLAY, P.A. (2018). Improving single-network single-channel separation of musical audio with convolutional layers. Proceedings of the 14th International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA). 

    XAMBÓ,  A., PAUWELS, J.,  ROMA, G., BARTHET, M. and FAZEKAS G. (2018) Jam with Jamendo: querying a large music collection by chords from a learner’s perspective. Proceedings of the 13th International Audio Mostly Conference. 

    ROMA, G., XAMBÓ,  A., GREEN, O. and TREMBLAY, P.A., (2018). A Javascript library for flexible visualization of audio descriptors.  Proceedings of the 4th Web Audio Conference (WAC). 

    XAMBÓ,  A., PAUWELS, J.,  ROMA, G., BARTHET, M. and FAZEKAS G., (2018) Exploring real-time visualisations to support chord learning with a large music collection. Proceedings of the 4th Web Audio Conference (WAC).

Courses taught on