{"url":"/dataset/podcastfillers","name":"PodcastFillers","full_name":null,"description_markdown":"The PodcastFillers dataset consists of 199 full-length podcast episodes in English with manually annotated filler words and automatically generated transcripts. The podcast audio recordings, sourced from SoundCloud, are CC-licensed, gender-balanced, and total 145 hours of audio from over 350 speakers. The annotations are provided under a non-commercial license and consist of 85,803 manually annotated audio events including approximately 35,000 filler words (“uh” and “um”) and 50,000 non-filler events such as breaths, music, laughter, repeated words, and noise. The annotated events are also provided as pre-processed 1-second audio clips. The dataset also includes automatically generated speech transcripts from a speech-to-text system. A detailed description is provided in Dataset.","description_withheld":null,"homepage":"https://podcastfillers.github.io/","introduced_date":"2022-03-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/filler-word-detection-and-classification-a","title":"Filler Word Detection and Classification: A Dataset and Benchmark","first_author":"Ge Zhu","url":null},"license":{"name":"Creative Commons Non-Commercial (Any)","url":"https://podcastfillers.github.io/license/"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Keyword Spotting","url":"/task/keyword-spotting","datasets_with_task":"/datasets/task/keyword-spotting"},{"name":"Sound Event Localization and Detection","url":"/task/sound-event-localization-and-detection","datasets_with_task":"/datasets/task/sound-event-localization-and-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["PodcastFillers"],"data_loaders":[],"num_papers_in_archive":5,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/sound-event-localization-and-detection-on-2","task":"Sound Event Localization and Detection","dataset_variant":"PodcastFillers","rows":2,"metrics":["event-based F1 score"],"first_row_in_archive_order":{"model":"AVC-FillerNet","paper":"/paper/filler-word-detection-and-classification-a","metrics":{"event-based F1 score":"92.8"},"code_links":[{"title":"gzhu06/PodcastFillers_Utils","url":"https://github.com/gzhu06/PodcastFillers_Utils"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/filler-word-detection-and-classification-a","title":"Filler Word Detection and Classification: A Dataset and Benchmark","date":"2022-03-28","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}