New method for computational analysis of sound chosen as JASA highlight

A recently published article by RITMO researchers has been chosen as a highlight by The Journal of the Acoustical Society of America (JASA).

Attack detection in audio samples described in the paper.

Attack detection in audio samples described in the paper.

Every month, JASA highlights four articles from that month's issue. In January's issue, Computational localization of attack regions through a direct observation of the audio waveform by Olivier Lartillot and collaborators Kristian Nymoen, Guilherme Schmidt C?mara and Anne Danielsen in the TIME project was chosen as a highlight. Highlighted articles are made accessible for free for a month after publication.

Read the article

Olivier Lartillot has developed a new method for the localisation of attack regions in audio recordings. Previous attempts to do so were based on reducing the audio waveform into an envelope curve, which decreases its temporal resolution. The proposed approach detects the attack region directly from the audio waveform and shows a significant increase in precision.

Lartillot is currently working on developing a comprehensive AI-based system for advanced music analysis in the MIRAGE project.

Published Feb. 11, 2021 2:45 PM - Last modified June 21, 2022 1:34 PM