Transcription-based video genre classification

In this paper, we present a new method for video genre identification based on the linguistic content analysis. This approach relies on the analysis of the most frequent words in the video transcriptions provided by an automatic speech recognition system. Experiments are conducted on a corpus composed of cartoons, movies, news, commercials, documentary, sport and music. On this 7-genre identification task, the proposed transcription-based method obtains up to 80% of correct identification. Finally, this rate is increased to 95% by combining the proposed linguistic-level features with lowlevel acoustic features.

• Type: Conference
• Year: 2010
• Where: ICASSP
• Authors: Stanislas Oger, Mickael Rouvier, Georges Linares
• Keywords: 7-genre Identification Task, Automatic Speech Recognition, ICASSP 2010, Linguistic Content Analysis, Signal Processing