Temporal Constructs
Inholland project on creative dialogue among humans, AI and digital heritage using small sustainable AI models.
Research
Papers, projects and labs working on AI music.
140 results
Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model
Research work examining audio generation, text-to-audio generation.
The Interpretation Gap in Text-to-Music Generation Models
Research work examining music generation, music retrieval.
Toward Universal Text-to-Music Retrieval
Research work examining evaluation benchmark, music retrieval.
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
Research work examining evaluation benchmark, music generation.
UniAudio: An Audio Foundation Model Toward Universal Audio Generation
Research work examining audio generation, singing voice.
UPF-BMAT Chair on Artificial Intelligence and Music
Cátedra UPF-BMAT en Inteligencia Artificial y Música
Public-private chair researching interpretable, transparent and accessible AI for music and training sector professionals.
Using Songs to Improve Kazakh Automatic Speech Recognition
LREC 2026 paper evaluating sung Kazakh data as a complementary source for low-resource ASR.
Video Soundtrack Generation by Aligning Emotions and Temporal Boundaries
Research paper introducing EMSYNC for emotion- and boundary-aligned symbolic soundtrack generation.
Video-based Music Generation
Doctoral work consolidating EMSYNC, video emotion classification and an emotion-labelled symbolic music dataset.
WavJourney: Compositional Audio Creation with Large Language Models
Research work examining audio generation, evaluation benchmark.
Whither Music?
JKU research project examining AI, music creativity and changing musical practices.