Description du projet
Des méthodes de calcul innovantes pour décrire les sons environnementaux
Les sons de la vie quotidienne peuvent apporter des informations précieuses sur notre environnement et les événements qui s’y déroulent. La technologie actuelle peine toutefois à identifier les sources sonores individuelles dans les paysages sonores complexes où de multiples sons sont présents et déformés par l’environnement. Pour résoudre ce problème, le projet EVERYSOUND, financé par le Conseil européen de la recherche, entend élaborer des méthodes informatiques capables de proposer automatiquement des descriptions de haut niveau des sons environnementaux. Le projet recourra à des techniques innovantes telles que la séparation conjointe des sources et des algorithmes robustes de classification des formes pour reconnaître de manière fiable plusieurs sons concomitants. En outre, il mettra au point une taxonomie multicouche hiérarchique afin de classer avec précision les sons de la vie quotidienne. Le projet proposera des outils précieux destinés aux études géographiques, sociales, culturelles et biologiques.
Objectif
Sounds carry a large amount of information about our everyday environment and physical events that take place in it. For example, when a car is passing by, one can perceive the approximate size and speed of the car. Sound can easily and unobtrusively be captured e.g. by mobile phones and transmitted further – for example, tens of hours of audio is uploaded to the internet every minute e.g. in the form of YouTube videos. However, today's technology is not able to recognize individual sound sources in realistic soundscapes, where multiple sounds are present, often simultaneously, and distorted by the environment.
The ground-breaking objective of EVERYSOUND is to develop computational methods which will automatically provide high-level descriptions of environmental sounds in realistic everyday soundscapes such as street, park, home, etc. This requires developing several novel methods, including joint source separation and robust pattern classification algorithms to reliably recognize multiple overlapping sounds, and a hierarchical multilayer taxonomy to accurately categorize everyday sounds. The methods are based on the applicant's internationally recognized and awarded expertise on source separation and robust pattern recognition in speech and music processing, which will allow now tackling the new and challenging research area of everyday sound recognition.
The results of EVERYSOUND will enable searching for multimedia based on its audio content, which is not possible with today's technology. It will allow mobile devices, robots, and intelligent monitoring systems to recognize activities in their environments using acoustic information. Producing automatically descriptions of vast quantities of audio will give new tools for geographical, social, cultural, and biological studies to analyze sounds related to human, animal, and natural activity in urban and rural areas, as well as multimedia in social networks.
Champ scientifique
- natural sciencescomputer and information sciencescomputational science
- natural sciencesphysical sciencesacoustics
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- natural sciencescomputer and information sciencesartificial intelligencepattern recognition
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Programme(s)
Thème(s)
Régime de financement
ERC-STG - Starting GrantInstitution d’accueil
33100 Tampere
Finlande