Last week we announced the publication of OpenBMAT, an open dataset for the tasks of music detection and relative music loudness estimation. The dataset contains 27.4 hours of audio from 8 different TV program types at 4 different countries, cross-annotated by 3 people using 6 different classes. It has been published as a dataset paper at Transaction of the International Society for Music Information Retrieval, the open journal of ISMIR. This research has been carried out as a collaboration between the MTG and BMAT in the context of the industrial Doctorates program of the Catalan Government.
For more information you can read the related news at MTG web site: https://www.upf.edu/web/mtg/home/-/asset_publisher/sWCQhjdDLWwE/content/id/227864284/maximized#.XXZ_IZMzab8
Two PhD students, Blai Meléndez-Català and Andrés Pérez-López, are joining my lab thanks to the industrial doctorate program from AGAUR, which supports collaboration between universities and industrial partners, in this case both from Barcelona. These students will work at the company but come to the lab for some time to interact and collaborate with us.
I will be the main academic supervisor of these projects, which are both linked to our research on audio processing and description, and dealing with large audio datasets and focusing on two particular problems:
- “Music/Speech Detection in Broadcast Media Programs” in collaboration with BMAT, in particular with Emilio Molina. Blai Meléndez Català is our PhD fellow, and the goal of this project is to research on the task of audio segmentation and tagging in the context audiovisual recordings.
- “Immersive Audiovisual Production Enhacement based on 3D Audio“, in collaboration with Fundación Eurecat, in particular with the audio-visual technologies group leaded by Adan Garriga. This project is related to 3D audio for virtual reality applications, and Andrés Pérez is a new PhD student that will research on innovative production tools for creative industries.
There is some more info (in catalan or spanish) on the UPF web site.