{"url":"/dataset/libricss","name":"LibriCSS","full_name":null,"description_markdown":"Continuous speech separation (CSS) is an approach to handling overlapped speech in conversational audio signals. A real recorded dataset, called **LibriCSS**, is derived from LibriSpeech by concatenating the corpus utterances to simulate a conversation and capturing the audio replays with far-field microphones.\r\n\r\nSource: [https://github.com/chenzhuo1011/libri_css](https://github.com/chenzhuo1011/libri_css)","description_withheld":null,"homepage":"https://github.com/chenzhuo1011/libri_css","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/continuous-speech-separation-dataset-and","title":"Continuous speech separation: dataset and analysis","first_author":"Zhuo Chen","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Speech Separation","url":"/task/speech-separation","datasets_with_task":"/datasets/task/speech-separation"},{"name":"Speaker Separation","url":"/task/speaker-separation","datasets_with_task":"/datasets/task/speaker-separation"}],"languages":[],"variants":["LibriCSS"],"data_loaders":[{"repo":"https://github.com/chenzhuo1011/libri_css","url":"https://github.com/chenzhuo1011/libri_css","frameworks":[]}],"num_papers_in_archive":73,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-recognition-on-libricss","task":"Speech Recognition","dataset_variant":"LibriCSS","rows":2,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"TS-SEP","paper":"/paper/ts-sep-joint-diarization-and-separation","metrics":{"Word Error Rate (WER)":"3.27"},"code_links":[{"title":"merlresearch/tssep","url":"https://github.com/merlresearch/tssep"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-separation-on-libricss","task":"Speech Separation","dataset_variant":"LibriCSS","rows":2,"metrics":["0S","0L","10%","20%","30%","40%"],"first_row_in_archive_order":{"model":"Conformer (large)","paper":"/paper/continuous-speech-separation-with-conformer","metrics":{"0L":"5.0","0S":"5.4","10%":"7.5","20%":"10.7","30%":"13.8","40%":"17.1"},"code_links":[{"title":"Sanyuan-Chen/CSS_with_Conformer","url":"https://github.com/Sanyuan-Chen/CSS_with_Conformer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/ts-sep-joint-diarization-and-separation","title":"TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings","date":"2023-03-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gpu-accelerated-guided-source-separation-for","title":"GPU-accelerated Guided Source Separation for Meeting Transcription","date":"2022-12-10","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/continuous-speech-separation-with-conformer","title":"Continuous Speech Separation with Conformer","date":"2020-08-13","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."}