{"url":"/dataset/csi","name":"CSI","full_name":null,"description_markdown":"**CSI** is a criminal conversational dataset for speaker identification built from the CSI television show. The authors collected transcripts of 39 episodes and video/audio of 4 episodes. Each episode involves on average more than 30 speakers. Utterances last on average 3 to 4 seconds. There are around 45 to 50 distinct scenes/conversations per episode.","description_withheld":null,"homepage":"https://github.com/maelfabien/Graph2Speak","introduced_date":"2020-09-21","introduced_date_note":null,"introduced_by":{"paper":"/paper/graph2speak-improving-speaker-identification","title":"Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data","first_author":null,"url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speaker Identification","url":"/task/speaker-identification","datasets_with_task":"/datasets/task/speaker-identification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CSI"],"data_loaders":[{"repo":"https://github.com/maelfabien/Graph2Speak","url":"https://github.com/maelfabien/Graph2Speak","frameworks":[]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}