Aktiviteter pr. år
Projektdetaljer
Beskrivelse
Productivity and well-being depends on digital media and the delivery of multimodal media information on many different platforms including TV, social, and mobile media. Traditional business models in the music, audio and broadcast sectors are challenged; however, the ubiquitous digitalization of media, localization information, and human behaviors has a huge and disruptive potential to be explored in strategic research. Audio information represents a separate challenge over other modalities (e.g. text or visual information) since it can be sensed and perceived as an abstract, emotional stream. Despite the fact that higher cognitive representations of audio are well-developed, they are not easily articulated or shared by nonexperts. This project focuses on methods and tools for an augmented audio experience and making the information actionable, i.e., enable users to interpret, organize, analyze, share, cocreate, and facilitate story-telling and audio management. The strong Danish position within sound technology together with the innovative approaches of this project will help unlock the potential. We propose a multi-disciplinary strategic research project lead by DTU including Danish research institutions, commercial partners, and end-users, as well as three major English university partners. The vision is to develop a flexible modular audio data processing platform for new products and services in the commercial sector; the public service sector; and in educational and cultural research. We will prototype and evaluate solutions in all these areas. The research will combine bottom-up representation of audio and other relevant information sources with top-down user-driven feedback.
Status | Afsluttet |
---|---|
Effektiv start/slut dato | 01/01/2012 → 31/12/2015 |
Fingerprint
Udforsk forskningsemnerne, som dette projekt berører. Disse etiketter er oprettet på grundlag af de underliggende bevillinger/legater. Sammen danner de et unikt fingerprint.
Aktiviteter
-
KTH School of Electrical Engineering
Sturm, B. L. (Gæsteforsker)
3 dec. 2012 → 7 dec. 2012Aktivitet: Gæsteophold ved andre institutioner
-
Music genre for humans and machines alike
Sturm, B. L. (Foredragsholder)
29 okt. 2012Aktivitet: Foredrag og mundtlige bidrag › Foredrag og præsentationer i privat eller offentlig virksomhed
-
Three experiments in music genre recognition
Sturm, B. L. (Oplægsholder)
14 sep. 2012Aktivitet: Foredrag og mundtlige bidrag › Foredrag og præsentationer i privat eller offentlig virksomhed
Publikation
-
Are deep neural networks really learning relevant features?
Kereliuk, C., Sturm, B. L. & Larsen, J., 2015.Publikation: Konferencebidrag uden forlag/tidsskrift › Konferenceabstrakt til konference › Forskning › peer review
-
A Closer Look at Deep Learning Neural Networks with Low-level Spectral Periodicity Features
Sturm, B. L., Kereliuk, C. & Pikrakis, A., 2014, Proceedings of 4th International Workshop on Cognitive Information Processing (CIP 2014). Hansen, L. K., Holdt Jensen, S. & Larsen, J. (red.). IEEE (Institute of Electrical and Electronics Engineers), Bind 1. s. 1-6 6 s.Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review
8 Citationer (Scopus) -
Classification Accuracy Is Not Enough: On the Evaluation of Music Genre Recognition Systems
Sturm, B. L., 2013, I: Journal of Intelligent Information Systems. 41, 3, s. 371-406 36 s.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review
Fil103 Citationer (Scopus)1764 Downloads (Pure)