People

spatial and immersive audio, music signal processing, machine learning for audio, music information retrieval

new interfaces for musical expression, performance study, human-computer interaction, interaction design

Communication acoustics, crossmodal correspondences, sound synthesis, cognitive audio, musical haptics

Machine listening / computer audition, Machine learning for audio and sequential data, Music information retrieval, Multimodal AI, Resource-efficient AI

Semantic Audio, Music Information Retrieval, Semantic Web for Music, Machine Learning and Data Science, Music Emotion Recognition, Interactive music sytems (e.g. intellignet editing, audio production and performance systems)

theoretical neuroscience, machine perception, artificial intelligence

automatic music labelling, music information retrieval, music signal processing, machine learning for audio, chord/key/structure (joint) estimation, instrument identification, multi-track/channel audio, music transcription, graphical models, big data science

signal processing; machine learning; robot perception

Music information research, Internet of musical things, Extended reality, New interfaces for musical expression, Semantic audio, Music perception (timbre, emotions), Audience-Performer interaction, Participatory art

Interaction Design, auditory displays, Data Sonification, Collaborative Systems, Cross-modal Interaction, Assistive Technology, Accessibility

new interfaces for musical expression, augmented instruments, performance study, human-computer interaction, embedded hardware

sound engineering, intelligent audio production, sound synthesis, audio effects, automatic mixing

Digital Signal Processing, Digital Audio, Music Informatics, Audio Features, Semantic Audio, Immersive Audio, Studio Science, Music Data Science, Music Linked Data.

Music informatics, music signal processing, artificial intelligence, music cognition; extraction of musical content (e.g. rhythm, harmony, intonation) from audio signals: beat tracking, audio alignment, chord and note transcription, singing intonation; using signal processing approaches, probabilistic models, and deep learning.

Music Cognition, Auditory Perception, Empirical Aesthetics, Statistical Learning, Probabilistic Modelling.

Computational Creativity, Artificial Intelligence, Music Cognition

computational linguistics including models of language and music

human interaction, human communication

Probabilistic learning of sequential structures in music cognition

Neuro-evolved Heuristics for Meta-composition

Self-supervision in Audio Fingerprinting

Beyond the fret: gesture analysis on fretted instruments and its applications to instrument augmentation

User-driven deep music generation in digital audio workstations

Real-Time Gesture Classification on an Augmented Acoustic Guitar using Deep Learning to Improve Extended-Range and Percussive Solo Playing

Deep Learning for Jazz Piano: Transcription + Generative Modeling

Computational analysis of chick vocalisations: from categorisation to live feedback

Latent Spaces for Human-AI music generation

Differentiable Digital Signal Processing, Audio Synthesis, and Symmetry

Towards Composing Contemporary Classical Music using Generative Deep Learning

The Sound of Care: researching the use of Deep Learning and Sonification for the daily support of people with Chronic Primary Pain

Enabling Efficient Training and Inference of Large Audio Models

Most people are familiar with Shazam, the app that recognizes recorded music using audio fingerprinting. It provides the title, artist, and other information from the audio of a song, as provided by the publisher. Shazam does not, however, work for live music. The topic of this thesis is song title recognition from live jazz.

Neural Drum Synthesis

Neural Audio Synthesis with Expressiveness Control

Music Interestingness in the Brain

End-to-end generative modeling of multitrack mixing with non-parallel data and adversarial networks

Deep Learning for Time-varying Audio Systems and Spectrotemporal Modulations

Deep learning for low-resource music

Perceptual end to end learning for music understanding

Modelling the Creative Process of Jazz Improvisation

Machine Learning of Physical Models for Voice Synthesis

Emotion-based Personalised Music Recommendation

Automatic micro-composition for professional/novice composers using generative models as creativity support tools

Optical music recognition using deep learning

Neural computing for auditory object analysis

AI Timbre Transfer for Low-Latency Musical Interaction

Artificial Neuroscience: Applying Mathematics to the Understanding and Control of Deep Learning

Analysis of Retro Aesthetics in Music Production

Representation learning for musical audio using graph neural network-based recommender engines

Timbre Tools for the Digital Instrument Maker

Informed source separation for multi-mic production

Computational Modelling of Expressive Piano Performance

Semantic understanding of TV programme content and structure to enable automatic enhancement and adjustment

Multimodal Deep Learning for Music Information Retrieval

Time to vibe together: cloud-based guitar and intelligent agent

Intelligent audio and music editing with deep learning

Lyrics Alignment For Polyphonic Music

Deep Generative Modelling for Expressive Piano Performance: From Symbolic Interpretation to Audio Realisation

Everyday Sound Recognition with Limited Annotations

Combining Deep Learning and Music Theory

Real-time timbral mapping for synthesized percussive performance

Beyond Supervised Learning for Musical Audio

Predicting hit songs: multimodal and data-driven approach

Neuro-Symbolic Automated Music Composition

Automatic audio-to-score piano transcription with deep neural networks

Meta-Physical Modelling

Neuro-symbolic music models

Gender-Coded Sound: A multimodal analysis of gender encoding strategies in music for advertising

Perception and analysis of 20th and 21st century popular music

Machine learning applied to sound synthesis models

Fast and Controllable Music Generation

Deep learning methods for multi-instrument music transcription

When XR Meets AI: Machine Learning for Gesture Control Mechanisms in XR Musical Instruments

Applications of deep learning for improved synthesis of engine sounds

An investigation evaluating realism in sound design

Generative Models For Music Audio Representation And Understanding

E-AIM - Embodied Cognition in Intelligent Musical Systems

Machine Learning of Physical Models

Multimodal AI for musical collaboration in immersive environments

Multi-modal Learning for Music Understanding

Hybrid Neural Methods for Sound Synthesis

Continuous mood recognition in film music

Character-based adaptive generative music for film and video games using Deep Learning and Hidden Markov Models

Style classification of podcasts using audio

Adaptive Music Generation for Video Game

Audio Applications of Novel Mathematical Methods in Deep Learning

Explainability of AI Music Generation

User-Centric Intelligent Context-Aware Multitrack Music Mixing

Sabotaging, errors and other mistakes as a source of new techniques in music improvisation

Sensor mesh as performance interface

Expressive Performance Rendering for Music Generation Systems

Predicting demographics, personalities, and global values from digital media behaviours

Machine Learning of Physical Models

Pitch tracking for music applications - beyond 99% accuracy

Automatic Mixing for teleconferencing, gaming and live streaming

Composition-aware music recommendation system for music production

Towards multilabel classification with joint audio-text models

Virtual Placement of Objects in Acoustic Scenes

Film score composer AI assistant: generating expressive mockups

Industry-scale Machine Listening for Music and Audio Data

Large Language Models for Music

Machine learning for physical models of sound synthesis

Improving Controllability and Editability for Pretrained Text-to-Music Generation Models

Personalizing Audio with Context-aware AI using Listener Preferences and Psychological Factors

Computational Comparison Between Different Genres of Music in Terms of the Singing Voice

Multimodal Foundational Models for Music

Project: Fine-grained music source separation with deep learning models

Networks able to display relationships between human and nonhuman actors. Project: Sensing the Forest.

music information retrieval, language models for music generation, guitar tablature generation, automatic guitar transcription, deep learning

Audio Source Separation, Music Information Retrieval, Sample Detection

Digital Signal Processing, Artificial Intelligence, Audio Effects Modelling

Sample Identification in Mastered Songs using Deep Learning Methods

Audio ML, Automatic Lyrics Transcription

Music Performance Assessment and Feedback

Projects: UKRI Centre for Doctoral Training in Artificial Intelligence and Music, New Frontiers in Music Information Processing (MIP-Frontiers)

Online Speech Enhancement In Scenarios With Low Direct-to-Reverberant-Ratio

Automated Music Performance Assessment and Critique

Towards multimodal self-supervised learning with application to audio classification

description