6 papers
Assessing AI-generated music detection in real-world broadcast monitoring
David López-Ayala, Fernando García de la Cruz, Pablo Zinemanas +2
The proliferation of AI-generated music in broadcast media raises concerns about transparency and fair compensation, but reliable detection under real broadcast conditions remains…
How Much AI Is in This Track? Quantifying the Proportion of AI-Generated Stems in Hybrid Music Mixtures
Fernando Garcia de la Cruz, David López-Ayala, Pablo Zinemanas +2
AI-generated music is increasingly used at the stem level, with producers integrating synthetic drums, basslines, or vocals alongside human-performed instruments. However, current…
AI-Generated Music Detection in Broadcast Monitoring
David López-Ayala, Asier Cabello, Pablo Zinemanas +2
AI music generators have advanced to the point where their outputs are often indistinguishable from human compositions. While detection methods have emerged, they are typically des…
Leveraging Pre-Trained Autoencoders for Interpretable Prototype Learning of Music Audio
Pablo Alonso-Jiménez, Leonardo Pepino, Roser Batlle-Roca +4
We present PECMAE, an interpretable model for music audio classification based on prototype learning. Our model is based on a previous method, APNet, which jointly learns an autoen…
FlowGrad: Using Motion for Visual Sound Source Localization
Rajsuryan Singh, Pablo Zinemanas, Xavier Serra +2
Most recent work in visual sound source localization relies on semantic audio-visual representations learned in a self-supervised manner, and by design excludes temporal informatio…
Soundata: A Python library for reproducible use of audio datasets
Magdalena Fuentes, Justin Salamon, Pablo Zinemanas +6
Soundata is a Python library for loading and working with audio datasets in a standardized way, removing the need for writing custom loaders in every project, and improving reprodu…