Research

Data descriptor for the DCML collection of annotated musical scores.

Research work examining music retrieval, music/audio understanding.

Research work examining evaluation benchmark, music transcription.

EPFL project developing data-driven and theoretical accounts of musical form.

IRCAM creative AI and data science research programme developing deep generative audio methods and tools.

Arts Council Malta awarded Culture Venture EUR 15,000 to study AI's effects on artists, including musicians, working conditions, ethics, and adoption barriers.

Technical University of Moldova thesis on an AI system for generating harmonically coherent chord progressions.

Research report on copyright questions raised by AI music outputs.

AI 프로듀서: 맞춤형 음악 창·제작 기술 개발

Joint Pozalabs, Supertone, and SNU project covering composition, analysis, and AI singing voice.

IIL project developing artist-controlled voice-synthesis systems from personal voice datasets.

APRA AMCOS survey report on generative AI adoption, cultural concerns and projected creator-revenue risk.

Turku UAS project testing AI applications with music professionals and producing practical guidance.

Machine-learning-aided performance system that listens to live audio and plays collaboratively with a human musician.

Inria Startup Studio project and public-facing brand developing the EVY neural MIDI arpeggiator; a separate legal entity was not verified.

Research work examining audio generation, evaluation benchmark.

Meta research library for deep-learning audio processing and generation, including MusicGen, AudioGen, EnCodec, and MAGNeT.

Research work examining audio generation, evaluation benchmark.

Research work examining audio generation, music/audio representation learning.

Research work examining evaluation benchmark, music/audio representation learning.

Conservatorium van Amsterdam research project on real-time collaboration between musicians and AI systems.

BioMúsica: Aplicações de Inteligência Artificial e Algoritmos Bio-Inspirados em Música

Brazilian research project applying artificial intelligence and bio-inspired algorithms to composition and improvisation.

Paper on classifying Brazilian music genres from a large lyrics dataset using a BLSTM network.

Pilot and 2026 catalogue-level expansion testing detection of likely AI-generated musical works.

Research work examining music/audio AI research.

Research work examining evaluation benchmark, music/audio representation learning.

Research work examining music generation, symbolic music.

Peer-reviewed review of computational creativity and music-generation systems by CSC researchers.

Research project investigating joint improvisation between human musicians and AI systems.

Research work examining text-to-music generation.

EPFL project using computational methods to study historical transitions of tonality.

Research work examining music generation.

ACM Multimedia 2025 dataset paper from Dublin City University researchers.

National report on AI use, attitudes and concerns in the Chilean music sector.

SGAE-backed study surveyed 1,257 music creators in Spain and reported adoption, concern, and projected rights-income impacts.

Peer-reviewed data paper documenting a Georgian vocal corpus and its MIR applications.

2026 evaluation of language models on South Asian music knowledge and controlled generation.

Research work examining music generation, symbolic music.

UvA project examining remuneration for musical works used in AI training in the Dutch music sector.

Research work examining evaluation benchmark, text-to-music generation.

Research work examining music generation, music/audio representation learning.

Research work examining evaluation benchmark, synthetic-audio detection.

Regional mixed-method research on AI use in music across Latin American countries.

ERC-funded research project on creative AI, embodied machine learning and intelligent musical instruments.

Research work examining music generation, text-to-music generation.

Research work examining music/audio editing, text-to-music generation.

Research work examining music generation, text-to-music generation.

Research paper describing design and analyses of JVS-MuSiC.

BMAT project researching content-auditing techniques intended to identify copyrighted material used by AI music systems.

LREC-COLING 2024 paper documenting the KazEmoTTS dataset and baseline synthesis model.

Research work examining music/audio understanding.

Legal research article on generative music AI under Colombian copyright and neighboring-rights law.

Research work examining music retrieval, music/audio representation learning.

Research work examining music generation, music retrieval.

Research work examining automatic accompaniment, evaluation benchmark.

Research work examining music retrieval, music/audio understanding.

Research work examining music generation, music/audio editing.

Research work examining evaluation benchmark, music/audio understanding.

Research work examining music/audio representation learning.

Research work examining evaluation benchmark, music retrieval.

Research work examining music/audio understanding.

MLP Singer: 빠른 병렬 한국어 가창 음성 합성을 향하여

Preprint describing a fast parallel Korean singing-voice synthesis architecture.

Research work examining evaluation benchmark, music/audio editing.

Research work examining evaluation benchmark, music/audio understanding.

Research work examining music transcription, music/audio understanding.

Infrastructure for music-related citizen-science listening experiments with current structural support.

Research article defining and evaluating the MUSIB benchmark.

Soluções de aprendizado de máquina para geração de música instrumental

USP master's dissertation evaluating GAN, VAE and LSTM approaches for instrumental music generation.

Study using chord-derived features and machine learning to predict genres in popular Brazilian music.

Open-source Google research project exploring machine learning as a tool in creative music and art processes.

Open-weights live music model and framework for low-latency, on-device interactive music generation.

Research work examining audio generation, evaluation benchmark.

Research work examining audio generation, text-to-audio generation.

KTH artificial folk-music composition project drawing on the FolkWiki tune archive.

Multi-institution research programme developing and studying co-creative AI, with dedicated music and artistic work.

Research work examining music generation, music/audio representation learning.

Paper presenting and benchmarking the Moises-Light source-separation architecture.

Infrastructure for controlled computational musicology access to the Montreux Jazz audiovisual archive.

Research work examining music generation, text-to-music generation.

Research work examining evaluation benchmark, music/audio understanding.

Research work examining music retrieval, music/audio representation learning.

Research work examining music transcription.

Research work examining evaluation benchmark, music/audio understanding.

Research work examining audio generation, music generation.

Research work examining music generation, symbolic music.

Research work examining evaluation benchmark, music generation.

Research work examining evaluation benchmark, music/audio representation learning.

Preprint applying MIDI feature extraction to representative Mexican folk vocal melodies.

Five-year UCL research programme examining the cultural implications of AI and music.

Research paper introducing music2latent for general-purpose audio compression.

Research work examining audio generation, music generation.

Research work examining music generation.

Research work examining music generation, music/audio editing.

Research work examining music generation, music provenance and watermarking.

Research demo training a U-Net to isolate surdo from Brazilian samba percussion mixtures.

Research work examining music generation, music retrieval.

MúsicaCL: música chilena y memoria colectiva

Public cultural-analytics output connecting Chilean music, collective memory, network science and AI-assisted exploration.

N-Singer: 한국어 발음 향상을 위한 비자기회귀 가창 음성 합성 시스템

Preprint proposing a parallel Korean singing-voice synthesis system.

Peer-reviewed Spanish-language article describing the NEA co-creative music system.

Paper describing the design of the open-source NNSVS toolkit.

Research work examining music generation, music/audio representation learning.

Research paper introducing the Notochord generative MIDI performance model.

Research paper describing the PJS corpus and its phoneme-balance and licensing design.

PEMANFAATAN MUSIK BUATAN AI MELALUI DEEPFAKE: STUDI HUKUM KOMPARATIF INDONESIA DAN AMERIKA SERIKAT

Comparative legal study of AI-made deepfake music under Indonesian and United States copyright law.

UPC project developing a real-time improvisation loop between a pianist and an AI system.

Research work examining music/audio AI research.

Five-year Orpheus Instituut research project examining AI and emerging technologies in music practice.

Posthuman Music: Creative Practices after AI and Blockchain

ERC Advanced Grant project investigating musical creative practice after AI and blockchain.

Research work examining evaluation benchmark, music/audio representation learning.

Research work examining music generation, singing voice.

Research paper introducing RAVE for fast high-quality neural audio synthesis.

ERC-linked IRCAM project researching cyber-human musical co-creativity and interactive agents.

Aalto research project applying generative models to restoration of music recordings.

2026 peer-reviewed work revisiting RWC as a community-driven MIR corpus.

Research work examining music generation, text-to-music generation.

Research work examining automatic accompaniment.

NTNU project developing custom datasets, generative models and prototypes for computer-assisted music making.

University of Luxembourg project researching AI-enhanced music performance and interaction.

LIM work package on AI HRTF modelling, spatial-hearing perception and real/virtual blending within the SONICOM project.

Research work examining singing voice, synthetic-audio detection.

Research work examining evaluation benchmark, music generation.

Research work examining singing voice, synthetic-audio detection.

Research work examining audio generation, automatic accompaniment.

Research work describing Sinsy's DNN-based singing synthesis architecture.

UAH project using AI to improve access to historical concert sources and preserve Chilean classical-music heritage.

Research work examining music/audio understanding.

Research paper introducing a dataset for auditing identity representation in text-to-music systems.

Research work examining text-to-audio generation.

Inholland project on creative dialogue among humans, AI and digital heritage using small sustainable AI models.

Research work examining audio generation, text-to-audio generation.

Research work examining music generation, music retrieval.

Research work examining evaluation benchmark, music retrieval.

Research work examining evaluation benchmark, music generation.

Cátedra UPF-BMAT en Inteligencia Artificial y Música

Public-private chair researching interpretable, transparent and accessible AI for music and training sector professionals.

Research work examining audio generation, singing voice.

LREC 2026 paper evaluating sung Kazakh data as a complementary source for low-resource ASR.

Research paper introducing EMSYNC for emotion- and boundary-aligned symbolic soundtrack generation.

Doctoral work consolidating EMSYNC, video emotion classification and an emotion-labelled symbolic music dataset.

Research work examining audio generation, evaluation benchmark.

JKU research project examining AI, music creativity and changing musical practices.

Paper and software note describing the musicnn pretrained model family.