An audio-only method for advertisement detection in broadcast television content
This provides a lightweight solution for broadcasters or advertisers needing efficient ad detection without video processing, though it is incremental as it adapts existing silence-based techniques to an audio-only context.
The paper tackles advertisement detection in broadcast television by using an audio-only method that identifies short silences at boundaries, achieving a Matthews correlation coefficient over 0.87 on a 26-hour Portuguese TV database and outperforming an audio-visual approach.
We address the task of advertisement detection in broadcast television content. While typically approached from a video-only or audio-visual perspective, we present an audio-only method. Our approach centres on the detection of short silences which exist at the boundaries between programming and advertising, as well as between the advertisements themselves. To identify advertising regions we first locate all points within the broadcast content with very low signal energy. Next, we use a multiple linear regression model to reject non-boundary silences based on features extracted from the local context immediately surrounding the silence. Finally, we determine the advertising regions based on the long-term grouping of detected boundary silences. When evaluated over a 26 hour annotated database covering national and commercial Portuguese television channels we obtain a Matthews correlation coefficient in excess of 0.87 and outperform a freely available audio-visual approach.