Improving automated segmentation of radio shows with audio embeddings
This work addresses segmentation for radio show analysis, but it is incremental as it builds on existing audio feature methods.
The study tackled the problem of automated topic segmentation of radio shows by using audio embeddings, finding that embeddings from a non-speech sound event classification task improved F1-measure by 32.3% compared to a text-only baseline.
Audio features have been proven useful for increasing the performance of automated topic segmentation systems. This study explores the novel task of using audio embeddings for automated, topically coherent segmentation of radio shows. We created three different audio embedding generators using multi-class classification tasks on three datasets from different domains. We evaluate topic segmentation performance of the audio embeddings and compare it against a text-only baseline. We find that a set-up including audio embeddings generated through a non-speech sound event classification task significantly outperforms our text-only baseline by 32.3% in F1-measure. In addition, we find that different classification tasks yield audio embeddings that vary in segmentation performance.