{"url":"/dataset/hui","name":"HUI speech corpus","full_name":"Hof University iisys speech dataset","description_markdown":"The data set contains several speakers. The 5 largest are listed individually, the rest are summarized as other.\r\nAll audio files have a sampling rate of 44.1kHz.\r\nFor each speaker, there is a clean variant in addition to the full data set, where the quality is even higher. Furthermore, there are various statistics.\r\nThe dataset can also be used for automatic speech recognition (ASR) if audio files are converted to 16 kHz.","description_withheld":null,"homepage":"https://opendata.iisys.de/datasets.html#hui-audio-corpus-german","introduced_date":"2021-06-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/hui-audio-corpus-german-a-high-quality-tts","title":"HUI-Audio-Corpus-German: A high quality TTS dataset","first_author":"Pascal Puchtler","url":null},"license":{"name":"Creative Commons BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"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":["HUI speech corpus"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automatic-speech-recognition-on-hui","task":"Automatic Speech Recognition (ASR)","dataset_variant":"HUI speech corpus","rows":1,"metrics":["WER (%)"],"first_row_in_archive_order":{"model":"Conformer Transducer","paper":"/paper/automatic-speech-recognition-in-german-a","metrics":{"WER (%)":"1.89%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-to-speech-synthesis-on-hui","task":"Text-To-Speech Synthesis","dataset_variant":"HUI speech corpus","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":"3.74"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/automatic-speech-recognition-in-german-a","title":"Automatic Speech Recognition in German: A Detailed Error Analysis","date":"2022-08-03","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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."}