Berker Banar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Berker Banar has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Simon Colton
Queen Mary University of London
4 shared publications - Nick Bryan-Kinns
University of the Arts London, London, United Kingdom
2 shared publications - Bingyuan Zhang
School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK
1 shared publication - Corey Ford
School of Electronic Engineering and Computer Science Mary University of London London E1 4NS UK
1 shared publication - Courtney Nicole Reed
Institute for Digital Technologies, Loughborough University London, London, United Kingdom
1 shared publication - Hasan Kocer
NANOTAM-Nanotechnology Research Center, Bilkent University, 06800 Ankara, Turkey
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 15 January 2024
- Published by Springer Nature in Machine Intelligence Research
- Vol. 21 (1) , 29-45
Exploring Variational Auto-encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI
Generative AI models for music and the arts in general are increasingly complex and hard to understand. The field of explainable AI (XAI) seeks to make complex and opaque AI models such as neural networks more understandable to people. One approach to making generative AI models more understandable is to impose a small number of semantically meaningful attributes on generative AI models. This paper contributes a systematic examination of the impact that different combinations of variational auto-encoder models (measureVAE and adversarialVAE), configurations of latent space in the AI model (from 4 to 256 latent dimensions), and training datasets (Irish folk, Turkish folk, classical, and pop) have on music generation performance when 2 or 4 meaningful musical attributes are imposed on the generative model. To date, there have been no systematic comparisons of such models at this level of combinatorial detail. Our findings show that measureVAE has better reconstruction performance than adversarialVAE which has better musical attribute independence. Results demonstrate that measureVAE was able to generate music across music genres with interpretable musical dimensions of control, and performs best with low complexity music such as pop and rock. We recommend that a 32 or 64 latent dimensional space is optimal for 4 regularised dimensions when using measureVAE to generate music across genres. Our results are the first detailed comparisons of configurations of state-of-the-art generative AI models for music and can be used to help select and configure AI models, musical features, and datasets for more understandable generation of music.
- 15 January 2024
- Published by Springer Nature in Machine Intelligence Research
- Vol. 21 (1) , 29-45
Top Cited PapersOpen AccessExploring Variational Auto-encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI
Generative AI models for music and the arts in general are increasingly complex and hard to understand. The field of explainable AI (XAI) seeks to make complex and opaque AI models such as neural networks more understandable to people. One approach to making generative AI models more understandable is to impose a small number of semantically meaningful attributes on generative AI models. This paper contributes a systematic examination of the impact that different combinations of variational auto-encoder models (measureVAE and adversarialVAE), configurations of latent space in the AI model (from 4 to 256 latent dimensions), and training datasets (Irish folk, Turkish folk, classical, and pop) have on music generation performance when 2 or 4 meaningful musical attributes are imposed on the generative model. To date, there have been no systematic comparisons of such models at this level of combinatorial detail. Our findings show that measureVAE has better reconstruction performance than adversarialVAE which has better musical attribute independence. Results demonstrate that measureVAE was able to generate music across music genres with interpretable musical dimensions of control, and performs best with low complexity music such as pop and rock. We recommend that a 32 or 64 latent dimensional space is optimal for 4 regularised dimensions when using measureVAE to generate music across genres. Our results are the first detailed comparisons of configurations of state-of-the-art generative AI models for music and can be used to help select and configure AI models, musical features, and datasets for more understandable generation of music.
- Open Access
Exploring XAI for the Arts: Explaining Latent Space in Generative Music
Explainable AI has the potential to support more interactive and fluid co-creative AI systems which can creatively collaborate with people. To do this, creative AI models need to be amenable to debugging by offering eXplainable AI (XAI) features which are inspectable, understandable, and modifiable. However, currently there is very little XAI for the arts. In this work, we demonstrate how a latent variable model for music generation can be made more explainable; specifically we extend MeasureVAE which generates measures of music. We increase the explainability of the model by: i) using latent space regularisation to force some specific dimensions of the latent space to map to meaningful musical attributes, ii) providing a user interface feedback loop to allow people to adjust dimensions of the latent space and observe the results of these changes in real-time, iii) providing a visualisation of the musical attributes in the latent space to help people understand and predict the effect of changes to latent space dimensions. We suggest that in doing so we bridge the gap between the latent space and the generated musical outcomes in a meaningful way which makes the model and its outputs more explainable and more debuggable.
Open AccessExploring XAI for the Arts: Explaining Latent Space in Generative Music
Explainable AI has the potential to support more interactive and fluid co-creative AI systems which can creatively collaborate with people. To do this, creative AI models need to be amenable to debugging by offering eXplainable AI (XAI) features which are inspectable, understandable, and modifiable. However, currently there is very little XAI for the arts. In this work, we demonstrate how a latent variable model for music generation can be made more explainable; specifically we extend MeasureVAE which generates measures of music. We increase the explainability of the model by: i) using latent space regularisation to force some specific dimensions of the latent space to map to meaningful musical attributes, ii) providing a user interface feedback loop to allow people to adjust dimensions of the latent space and observe the results of these changes in real-time, iii) providing a visualisation of the musical attributes in the latent space to help people understand and predict the effect of changes to latent space dimensions. We suggest that in doing so we bridge the gap between the latent space and the generated musical outcomes in a meaningful way which makes the model and its outputs more explainable and more debuggable.
- Open Access
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16401-16403
A Tool for Generating Controllable Variations of Musical Themes Using Variational Autoencoders with Latent Space Regularisation
A common musical composition practice is to develop musical pieces using variations of musical themes. In this study, we present an interactive tool which can generate variations of musical themes in real-time using a variational autoencoder model. Our tool is controllable using semantically meaningful musical attributes via latent space regularisation technique to increase the explainability of the model. The tool is integrated into an industry standard digital audio workstation - Ableton Live - using the Max4Live device framework and can run locally on an average personal CPU rather than requiring a costly GPU cluster. In this way we demonstrate how cutting-edge AI research can be integrated into the exiting workflows of professional and practising musicians for use in the real-world beyond the research lab.
- 26 June 2023
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (13) , 16401-16403
Open AccessA Tool for Generating Controllable Variations of Musical Themes Using Variational Autoencoders with Latent Space Regularisation
A common musical composition practice is to develop musical pieces using variations of musical themes. In this study, we present an interactive tool which can generate variations of musical themes in real-time using a variational autoencoder model. Our tool is controllable using semantically meaningful musical attributes via latent space regularisation technique to increase the explainability of the model. The tool is integrated into an industry standard digital audio workstation - Ableton Live - using the Max4Live device framework and can run locally on an average personal CPU rather than requiring a costly GPU cluster. In this way we demonstrate how cutting-edge AI research can be integrated into the exiting workflows of professional and practising musicians for use in the real-world beyond the research lab.
- 15 April 2022
- Published by Springer Nature
- p. 19-35
A Systematic Evaluation of GPT-2-Based Music Generation
- 15 April 2022
- Published by Springer Nature
- p. 19-35
A Systematic Evaluation of GPT-2-Based Music Generation
- 20 April 2015
- Published by AIP Publishing in Applied Physics Letters
- Vol. 106 (16) , 161104
Thermal tuning of infrared resonant absorbers based on hybrid gold-VO2 nanostructures
Resonant absorbers based on plasmonic materials, metamaterials, and thin films enable spectrally selective absorption filters, where absorption is maximized at the resonance wavelength. By controlling the geometrical parameters of nano/microstructures and materials' refractive indices, resonant absorbers are designed to operate at wide range of wavelengths for applications including absorption filters, thermal emitters, thermophotovoltaic devices, and sensors. However, once resonant absorbers are fabricated, it is rather challenging to control and tune the spectral absorption response. Here, we propose and demonstrate thermally tunable infrared resonant absorbers using hybrid gold-vanadium dioxide (VO2) nanostructure arrays. Absorption intensity is tuned from 90% to 20% and 96% to 32% using hybrid gold-VO2 nanowire and nanodisc arrays, respectively, by heating up the absorbers above the phase transition temperature of VO2 (68 °C). Phase change materials such as VO2 deliver useful means of altering optical properties as a function of temperature. Absorbers with tunable spectral response can find applications in sensor and detector applications, in which external stimulus such as heat, electrical signal, or light results in a change in the absorption spectrum and intensity.
- 20 April 2015
- Published by AIP Publishing in Applied Physics Letters
- Vol. 106 (16) , 161104
Thermal tuning of infrared resonant absorbers based on hybrid gold-VO2 nanostructures
Resonant absorbers based on plasmonic materials, metamaterials, and thin films enable spectrally selective absorption filters, where absorption is maximized at the resonance wavelength. By controlling the geometrical parameters of nano/microstructures and materials' refractive indices, resonant absorbers are designed to operate at wide range of wavelengths for applications including absorption filters, thermal emitters, thermophotovoltaic devices, and sensors. However, once resonant absorbers are fabricated, it is rather challenging to control and tune the spectral absorption response. Here, we propose and demonstrate thermally tunable infrared resonant absorbers using hybrid gold-vanadium dioxide (VO2) nanostructure arrays. Absorption intensity is tuned from 90% to 20% and 96% to 32% using hybrid gold-VO2 nanowire and nanodisc arrays, respectively, by heating up the absorbers above the phase transition temperature of VO2 (68 °C). Phase change materials such as VO2 deliver useful means of altering optical properties as a function of temperature. Absorbers with tunable spectral response can find applications in sensor and detector applications, in which external stimulus such as heat, electrical signal, or light results in a change in the absorption spectrum and intensity.