Detecting Extraneous Content in Podcasts

TL;DR

This paper introduces classifiers that utilize textual and listening pattern analysis to identify extraneous content in podcasts, improving summarization quality by reducing irrelevant material and enhancing ROUGE scores.

Contribution

The study presents a novel approach combining textual and listening features for detecting extraneous podcast content, which improves summarization accuracy.

Findings

Enhanced ROUGE scores in podcast summarization

Effective detection of extraneous content

Reduction of irrelevant material in summaries

Abstract

Podcast episodes often contain material extraneous to the main content, such as advertisements, interleaved within the audio and the written descriptions. We present classifiers that leverage both textual and listening patterns in order to detect such content in podcast descriptions and audio transcripts. We demonstrate that our models are effective by evaluating them on the downstream task of podcast summarization and show that we can substantively improve ROUGE scores and reduce the extraneous content generated in the summaries.