Audio Event Detection in Movies using Multiple Audio Words and Contextual Bayesian Networks

Cédric Penet 1, 2 Claire-Hélène Demarty 1 Guillaume Gravier 1, 2 Patrick Gros 1, 2
2 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : This article investigates a novel use of the well known audio words representations to detect specific audio events, namely gunshots and explosions, in order to get more robustness towards soundtrack variability in Hollywood movies. An audio stream is processed as a sequence of stationary segments. Each segment is described by one or several audio words obtained by applying product quantization to standard features. Such a representation using multiple audio words constructed via product quantisation is one of the novelties described in this work. Based on this representation, Bayesian networks are used to exploit the contextual information in order to detect audio events. Experiments are performed on a comprehensive set of 15 movies, made publicly available. Results are comparable to the state of the art results obtained on the same dataset but show increased robustness to decision thresholds, however limiting the range of possible operating points in some conditions. Late fusion provides a solution to this issue.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal.inria.fr/hal-00822022
Contributor : Cédric Penet <>
Submitted on : Monday, May 13, 2013 - 6:09:26 PM
Last modification on : Friday, November 16, 2018 - 1:23:15 AM
Long-term archiving on : Wednesday, August 14, 2013 - 5:50:07 AM

File

CBMI2013_CedricPENET_CameraRea...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00822022, version 1

Citation

Cédric Penet, Claire-Hélène Demarty, Guillaume Gravier, Patrick Gros. Audio Event Detection in Movies using Multiple Audio Words and Contextual Bayesian Networks. CBMI - 11th International Workshop on Content Based Multimedia Indexing - 2013, Jun 2013, Veszprém, Hungary. ⟨hal-00822022⟩

Share

Metrics

Record views

1390

Files downloads

468