Audio-Based Video Genre Identification - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Audio-Based Video Genre Identification

Stanislas Oger
  • Function : Author
  • PersonId : 770872
  • IdRef : 176527176
Georges Linares
Driss Matrouf
Yingbo Li
  • Function : Author

Abstract

—This paper presents investigations about the automatic identification of video genre by audio channel analysis. Genre refers to editorial styles such commercials, movies, sports… We propose and evaluate some methods based on both low and high level descriptors, in cepstral or time domains, but also by analyzing the global structure of the document and the linguistic contents. Then, the proposed features are combined and their complementarity is evaluated. On a database composed of single-stories web-videos, the best audio-only based system performs 9% of Classification Error Rate (CER). Finally, we evaluate the complementarity of the proposed audio features and video features that are classically used for Video Genre Identification (VGI). Results demonstrate the complementarity of the modalities for genre recognition, the final audio-video system reaching 6% CER.
No file

Dates and versions

hal-01340017 , version 1 (30-06-2016)

Identifiers

Cite

Mickael Rouvier, Stanislas Oger, Georges Linares, Driss Matrouf, Bernard Merialdo, et al.. Audio-Based Video Genre Identification. TASLP 2015 Transactions on Audio Speech and Language, 2015, Piscataway, United States. ⟨10.1109/TASLP.2014.2387411⟩. ⟨hal-01340017⟩
160 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More