ICDAR 2023

Picture of John
- 11 months ago
Juan Carlos ICDAR 1 - Repertorium AI will revolutionise music scholarship, enhance streaming revenues, and empower musicians

Juan Carlos Martínez Sevilla presented his paper “A Holistic Approach for Aligned Music and Lyrics Transcription” at the International Conference on Document Analysis and Recognition (ICDAR) in San José, California, USA. Their paper introduces an approach to the Aligned Music Notation and Lyrics Transcription (AMNLT) challenge, which is to retrieve content from images of vocal music by developing data-driven approaches that transcribe music and text while providing proper alignment. Their holistic neural approaches achieve significant improvements over existing methods in transcription and alignment metrics.

Martinez Sevilla, Juan C. & Ríos Vila, Antonio & Castellanos, Francisco & Calvo-Zaragoza, Jorge. (2023). A Holistic Approach for Aligned Music and Lyrics Transcription.

Sign up to our Newsletter to stay informed!


Get in touch if you have any questions!

The Project

REPERTORIUM uses AI to digitise ancient and classical manuscripts, preserve European musical heritage, and create state-of-the-art sound processing technologies, including metaverse-ready immersive audio. These technologies are the foundation of a general musical artificial intelligence that fully unleashes the powers of machine learning upon the domain of European classical heritage, advancing us towards a human-centred digital world.