2022/03/28 by Ge Zhu, Zhu, Ge, Juan-Pablo Cáceres +3 · 1 citation
Computer Science · Social Sciences · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Radio, Podcasts, and Digital Media #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2203.15135
openalex publication_date 2022/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 to date. A key reason is the absence of a dataset with annotated filler words for model 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, laughter, 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, in the hope that our work serves as a benchmark for future research.