Filler Word Detection and Classification: A Dataset and Benchmark

Filler words such as ‘uh’ or ‘um’ are sounds or words people use to signal they are pausing to think. Finding and removing filler words from recordings is a common and tedious task in media editing. Automatically detecting and classifying filler words could greatly aid in this task, but few studies have been published on this problem. A key reason is the absence of a dataset with annotated filler words for training and evaluation. In this work, we present a novel speech dataset, PodcastFillers, with 35K annotated filler words and 50K annotations of other sounds that commonly occur in podcasts such as breaths, laugh-ter, and word repetitions. We propose a pipeline that leverages VAD and ASR to detect filler candidates and a classifier to distinguish between filler word types. We evaluate our proposed pipeline on PodcastFillers, compare to several baselines, and present a detailed ablation study. In particular, we evaluate the importance of using ASR and how it compares to a transcription-free approach resembling keyword spotting. We show that our pipeline obtains state-of-the-art results, and that leveraging ASR strongly outperforms a keyword spotting approach. We make PodcastFillers publicly available, and hope our work serves as a benchmark for future research. Using PodcastFillers, we train a filler classifier similar to a keyword spotting approach, and present an end-to-end pipeline that leverages VAD, ASR, and the classifier to perform filler word detection and classification. We compare our proposed pipeline to two baselines and show that it yields state-of the-art results. We hope it serves as a robust benchmark for future research.

Paper

Similar papers

© 2026 NYSGPT2525 LLC