{"url":"/dataset/thorsten-voice-21-02-neutral","name":"Thorsten voice 21.02 neutral","full_name":null,"description_markdown":"Thorsten-Voice (Thorsten-21.02-neutral) is a neutrally spoken voice dataset recorded by Thorsten Müller, audio optimized by Dominik Kreutz and licenced under CC0 to provide it for anybody without any financial or licence struggle. It is intended to be used for speech synthesis in German as a single speaker dataset. It contains about 23 hours of high quality audio","description_withheld":null,"homepage":"https://zenodo.org/record/5525342#.Y3Kq_ceZOcs","introduced_date":"2021-02-01","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC0","url":"https://creativecommons.org/choose/zero/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"}],"languages":[{"name":"German","url":"/datasets/language/german"}],"variants":["Thorsten voice 21.02 neutral"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-speech-synthesis-on-thorsten-voice-21","task":"Text-To-Speech Synthesis","dataset_variant":"Thorsten voice 21.02 neutral","rows":1,"metrics":["Mean Opinion Score"],"first_row_in_archive_order":{"model":"Tacotron 2","paper":"/paper/neural-speech-synthesis-in-german","metrics":{"Mean Opinion Score":"3.49"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/neural-speech-synthesis-in-german","title":"Neural Speech Synthesis in German","date":"2021-10-03","rows_on_this_dataset":1,"code_links":0,"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."}