ISCA Archive SLAM 2013
ISCA Archive SLAM 2013

Processing and linking audio events in large multimedia archives: the EU inevent project

Hervé Bourlard, Marc Ferràs, Nikolaos Pappas, Andrei Popescu-Belis, Steve Renals, Fergus McInnes, Peter J. Bell, Sandy Ingram, Mael Guillemot

In the inEvent EU project [1], we aim at structuring, retrieving, and sharing large archives of networked, and dynamically changing, multimedia recordings, mainly consisting of meetings, videoconferences, and lectures. More specifically, we are developing an integrated system that performs audiovisual processing of multimedia recordings, and labels them in terms of interconnected “hyper-events” (a notion inspired from hyper-texts). Each hyper-event is composed of simpler facets, including audio-video recordings and metadata, which are then easier to search, retrieve and share. In the present paper, we mainly cover the audio processing aspects of the system, including speech recognition, speaker diarization and linking (across recordings), the use of these features for hyper-event indexing and recommendation, and the search portal. We present initial results for feature extraction from lecture recordings using the TED talks.

"Accessing dynamic networked multimedia events," in EU Project No. 287872, Network Media. [Online]. Available: https://www.inevent-project.eu/

Index Terms: Networked multimedia events; audio processing: speech recognition; speaker diarization and linking; multimedia indexing and searching; hyper-events.


Cite as: Bourlard, H., Ferràs, M., Pappas, N., Popescu-Belis, A., Renals, S., McInnes, F., Bell, P.J., Ingram, S., Guillemot, M. (2013) Processing and linking audio events in large multimedia archives: the EU inevent project. Proc. First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), 3-8

@inproceedings{bourlard13_slam,
  author={Hervé Bourlard and Marc Ferràs and Nikolaos Pappas and Andrei Popescu-Belis and Steve Renals and Fergus McInnes and Peter J. Bell and Sandy Ingram and Mael Guillemot},
  title={{Processing and linking audio events in large multimedia archives: the EU inevent project}},
  year=2013,
  booktitle={Proc. First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013)},
  pages={3--8}
}