Lecturer in Digital Music Processing
Chair of the EECS Devolved School Research Ethics Committee
Communication acoustics, Music informatics, Machine learning and AI, Computational Creativity, Human-computer interaction, Computational social science
Publications of specific relevance to the Centre for Human-Centred Computing
Evaluating Foundation Models on Timbre-Related Cognitive TasksAssessing the Alignment of Audio Representations with Timbre Similarity RatingsPredicting Moral Values in Lyrics Through Audio(De)Constructing Timbre at NIME: Reflecting on Technology and Aesthetic Entanglements in Instrument DesignAudio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matchingMamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music GenerationDesigning Neural Synthesizers for Low-Latency InteractionHybrid Losses for Hierarchical Embedding LearningHybrid Losses for Hierarchical Embedding LearningA multimodal understanding of the role of sound and music in gendered toy marketingComposer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion ModelsTimbre Tools: Ethnographic Perspectives on Timbre and Sonic Cultures in Hackathon DesignsBuilding Sketch-to-Sound Mapping with Unsupervised Feature Extraction and Interactive Machine LearningMoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social DiscussionsFoundation Models for Music: A SurveyTimbral brightness perception investigated through multimodal interferenceAutomatic Detection of Moral Values in Music LyricsDeep Learning-based Audio Representations for the Analysis and Visualisation of Electronic Dance Music DJ MixesExplainable Modeling of Gender-Targeting Practices in Toy Advertising Sound and MusicMoralBERT: A Fine-Tuned Language Model for Capturing Moral Values in Social DiscussionsTimbral effects of col legno tratto techniques on bowed cello soundsComposer Style-Specific Symbolic Music Generation using Vector Quantized Discrete Diffusion ModelsA review of differentiable digital signal processing for music and speech synthesisSoundscapes of morality: Linking music preferences and moral values through lyrics and audioGender-Coded Sound: Analysing the Gendering of Music in Toy Commercials via Multi-Task LearningComposer Style-specific Symbolic Music Generation Using Vector Quantized Discrete Diffusion ModelsFast Diffusion GAN Model for Symbolic Music Generation Controlled by EmotionsSound of Care: Towards a Co-Operative AI Digital Pain Companion to Support People with Chronic Primary PainDifferentiable Modelling of Percussive Audio with Transient and Spectral SynthesisDifferentiable Modelling of Percussive Audio with Transient and Spectral SynthesisA Review of Differentiable Digital Signal Processing for Music & Speech SynthesisSinusoidal Frequency Estimation by Gradient DescentRigid-Body Sound Synthesis with Differentiable Modal ResonatorsInteractive Neural ResonatorsInteractive Neural ResonatorsThe Responsibility Problem in Neural Networks with Unordered TargetsThe language of sounds unheard: Exploring musical timbre semantics of large language modelsTimbre Semantic Associations Vary Both Between and Within InstrumentsModelling Moral Traits with Music Listening Preferences and DemographicsRigid-Body Sound Synthesis with Differentiable Modal ResonatorsSinusoidal Frequency Estimation by Gradient DescentMore Than Words: Linking Music Preferences and Moral Values Through LyricsTimbre Transfer with Variational Auto Encoding and Cycle-Consistent Adversarial NetworksDisembodied Timbres: A Study on Semantically Prompted FM SynthesisDeep Embeddings for Robust User-Based Amateur Vocal Percussion ClassificationDeep Conditional Representation Learning for Drum Sample Retrieval by VocalisationPrefaceDeep Embeddings for Robust User-Based Amateur Vocal Percussion Classificationtimbre.fun: A gamified interactive system for crowdsourcing a timbre semantic vocabularyNeural Waveshaping SynthesisLearning Models for Query by Vocal Percussion: A Comparative StudyTimbre Transfer with Variational Auto Encoding and Cycle-Consistent Adversarial NetworksA Modulation Front-End for Music Audio TaggingModelling Moral Traits with Music Listening Preferences and Demographics20 NIMEs: Twenty Years of New Interfaces for Musical ExpressionA Modulation Front-End for Music Audio TaggingPhoneme Mappings for Online Vocal Percussion TranscriptionThe Timbre Explorer: A Synthesizer Interface for Educational Purposes and Perceptual StudiesLearning Models for Query by Vocal Percussion: A Comparative StudyBrightness perception for musical instrument sounds: Relation to timbre dissimilarity and source-cause categoriesTimbre Space Representation of a Subtractive SynthesizerSpectral and Temporal Timbral Cues of Vocal Imitations of Drum SoundsTimbre Space Representation of a Subtractive SynthesizerThere’s more to timbre than musical instruments: semantic dimensions of FM soundsEvidence for timbre space robustness to an uncontrolled online stimulus presentationMusical dynamics classification with CNN and modulation spectraTimbre semantics through the lens of crossmodal correspondences: A new way of asking old questionsTimbre: Acoustics, Perception, and CognitionThe Semantics of TimbreAudio Content Descriptors of TimbreThe Present, Past, and Future of Timbre ResearchMultimodal Classification of Stressful Environments in Visually Impaired Mobility Using EEG and Peripheral BiosignalsMultimodal Classification of Stressful Environments in Visually Impaired Mobility Using EEG and Peripheral BiosignalsMusical HapticsMusical Haptics: IntroductionThe Role of Haptic Cues in Musical Instrument Quality PerceptionCognitive Load Assessment from EEG and Peripheral Biosignals for the Design of Visually Impaired Mobility AidsConcepts of timbre emerging from musician linguistic expressionsPerceptual evaluation of violins: A psycholinguistic analysis of preference verbal descriptions by experienced musicians.Fractal Art: Closer to Heaven? Modern Mathematics, the Art of Nature, and the Nature of ArtExploring multimodal biosignal features for stress detection during indoor mobilityModel-based obstacle sonification for the navigation of visually impaired personsSound of Vision - Spatial Audio Output and Sonification ApproachesIdentifying Urban Mobility Challenges for the Visually Impaired with Mobile Monitoring of Multimodal BiosignalsPost-Classification of Nominally Identical Steel-String Guitars Using Bridge AdmittancesEffect of Task Constraints on the Perceptual Evaluation of ViolinsCorrecting Large-Scale OMR Data with CrowdsourcingCategorization and lexicon in verbal descriptions of violin quality by performersPerceptual evaluation of violins: A comparison of intra-individual agreement in playing vs. listening tasks for the case of richnessPerceptual evaluation of violins: A comparison of intra-individual agreement in playing vs. listening tasks for the case of richnessPerceptual evaluation of violins: A quantitative analysis of preference judgments by experienced playersInvestigating the origin of inter-individual differences in the preference for violinsAspects of experimental design for the perceptual evaluation of violin qualitiesEvaluating violin quality: How consistent are skilled players?Physical modeling of the piano: An investigation into the effect of string stiffness on the hammer string interaction.Designing Neural Synthesizers for Low-Latency InteractionDesigning Percussive Timbre Remappings: Negotiating Audio Representations and Evolving Parameter SpacesSonicolour: Exploring Colour Control of Sound Synthesis with Interactive Machine LearningMamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music GenerationAssessing the Alignment of Audio Representations with Timbre Similarity RatingsLeveraging RAG for a Low-Resource Audio-Aware Diachronic Analysis of Gendered Toy MarketingAudio synthesizer inversion in symmetric parameter spaces with approximately equivariant flow matchingWhat do people know about the senses? Understanding perceptions of variation in sensory experienceDisembodied Timbres: a Study on Semantically Prompted FM SynthesisSoundscapes of morality: Linking music preferences and moral values through lyrics and audioA Multimodal Understanding of the Role of Sound and Music in Gendered Toy MarketingReal-time Timbre Remapping with Differentiable DSPGrants of specific relevance to the Centre for Human-Centred ComputingSmart EQ: Personalising Audio with Context-aware AI using Listener Preferences and Psychological FactorsUKRI Centre for Doctoral Training in Artificial Intelligence and MusicInternship Vjosa Preniqi: Analysing User Activity for Improving Recommendations in Streaming PlatformsMetaphors we listen with: The neural correlates of timbral brightness investigated by pitch-timbre interference and fMRIWe are delighted to share that CMAI PhD student Ben Hayes, along with CMAI academics Charalampos Saitis and George Fazekas, have received the best student paper award at the ISMIR 2025 conference. The paper "Audio Synthesizer Inversion in Symmetric Parameter Spaces With Approximately Equivariant Flow Matching" proposes using permutation equivariant continuous ... [more]
On 21-25 September 2025, several CMAI researchers will participate at the 26th International Society for Music Information Retrieval Conference (ISMIR 2025). ISMIR is the leading conference in the field of music informatics, and is currently the top-cited publication for Music & Musicology (source: Google Scholar). This year ISMIR will take place onsite in ... [more]
On 30 June - 5 July 2025, CMAI researchers will participate at the IEEE International Joint Conference on Neural Networks (IJCNN 2025), the flagship conference of the IEEE Computational Intelligence Society and the International Neural Network Society. The Centre for Multimodal AI will have a strong presence at the conference. The following papers authored/... [more]
On 6-11 April 2025, several CMAI researchers will participate at the 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025). ICASSP is the leading conference in the field of signal processing and the flagship event of the IEEE Signal Processing Society. As in previous years, the Centre for Multimodal AI ... [more]
