{"url":"/dataset/vctk","name":"VCTK","full_name":"CSTR VCTK Corpus","description_markdown":"This CSTR **VCTK** Corpus includes speech data uttered by 110 English speakers with various accents. Each speaker reads out about 400 sentences, which were selected from a newspaper, the rainbow passage and an elicitation paragraph used for the speech accent archive. The newspaper texts were taken from Herald Glasgow, with permission from Herald & Times Group. Each speaker has a different set of the newspaper texts selected based a greedy algorithm that increases the contextual and phonetic coverage. The details of the text selection algorithms are described in the following paper: C. Veaux, J. Yamagishi and S. King, \"The voice bank corpus: Design, collection and data analysis of a large regional accent speech database,\" https://doi.org/10.1109/ICSDA.2013.6709856. The rainbow passage and elicitation paragraph are the same for all speakers. The rainbow passage can be found at International Dialects of English Archive: (http://web.ku.edu/~idea/readings/rainbow.htm). The elicitation paragraph is identical to the one used for the speech accent archive (http://accent.gmu.edu). The details of the the speech accent archive can be found at http://www.ualberta.ca/~aacl2009/PDFs/WeinbergerKunath2009AACL.pdf. All speech data was recorded using an identical recording setup: an omni-directional microphone (DPA 4035) and a small diaphragm condenser microphone with very wide bandwidth (Sennheiser MKH 800), 96kHz sampling frequency at 24 bits and in a hemi-anechoic chamber of the University of Edinburgh. (However, two speakers, p280 and p315 had technical issues of the audio recordings using MKH 800). All recordings were converted into 16 bits, were downsampled to 48 kHz, and were manually end-pointed.\r\n\r\nSource: [CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)](https://datashare.is.ed.ac.uk/handle/10283/3443)","description_withheld":null,"homepage":"https://datashare.is.ed.ac.uk/handle/10283/2651","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":null,"title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","first_author":null,"url":"http://dx.doi.org/10.7488/ds/1994"},"license":{"name":"Creative Commons License: Attribution 4.0 International","url":"https://datashare.ed.ac.uk/bitstream/handle/10283/2651/license_text?sequence=3&isAllowed=y"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Bandwidth Extension","url":"/task/bandwidth-extension","datasets_with_task":"/datasets/task/bandwidth-extension"},{"name":"Audio Super-Resolution","url":"/task/audio-super-resolution","datasets_with_task":"/datasets/task/audio-super-resolution"},{"name":"Voice Conversion","url":"/task/voice-conversion","datasets_with_task":"/datasets/task/voice-conversion"},{"name":"Directional Hearing","url":"/task/directional-hearing","datasets_with_task":"/datasets/task/directional-hearing"},{"name":"Real-time Directional Hearing","url":"/task/real-time-directional-hearing","datasets_with_task":"/datasets/task/real-time-directional-hearing"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"}],"variants":["Voice Bank corpus (VCTK)","VCTK Multi-Speaker","VCTK"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/vctk","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/CSTR-Edinburgh/vctk","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/vctk-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/vctk","frameworks":["tf","jax"]},{"repo":"https://github.com/pytorch/audio","url":"https://pytorch.org/audio/stable/datasets.html#torchaudio.datasets.VCTK","frameworks":["pytorch"]}],"num_papers_in_archive":476,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-super-resolution-on-vctk-multi-speaker-1","task":"Audio Super-Resolution","dataset_variant":"VCTK Multi-Speaker","rows":7,"metrics":["Log-Spectral Distance"],"first_row_in_archive_order":{"model":"CMGAN","paper":"/paper/cmgan-conformer-based-metric-gan-for-monaural","metrics":{"Log-Spectral Distance":"0.76"},"code_links":[{"title":"ruizhecao96/cmgan","url":"https://github.com/ruizhecao96/cmgan"},{"title":"SherifAbdulatif/CMGAN","url":"https://github.com/SherifAbdulatif/CMGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/audio-super-resolution-on-voice-bank-corpus-1","task":"Audio Super-Resolution","dataset_variant":"Voice Bank corpus (VCTK)","rows":3,"metrics":["Log-Spectral Distance"],"first_row_in_archive_order":{"model":"U-Net + AFiLM","paper":"/paper/self-attention-for-audio-super-resolution","metrics":{"Log-Spectral Distance":"2.3"},"code_links":[{"title":"ncarraz/AFILM","url":"https://github.com/ncarraz/AFILM"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/bandwidth-extension-on-vctk","task":"Bandwidth Extension","dataset_variant":"VCTK","rows":1,"metrics":["LSD"],"first_row_in_archive_order":{"model":"AERO","paper":"/paper/aero-audio-super-resolution-in-the-spectral","metrics":{"LSD":"0.77"},"code_links":[{"title":"slp-rl/aero","url":"https://github.com/slp-rl/aero"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/directional-hearing-on-vctk","task":"Directional Hearing","dataset_variant":"VCTK","rows":1,"metrics":["SI-SDRi"],"first_row_in_archive_order":{"model":"HybridBeam+","paper":"/paper/hybrid-neural-networks-for-on-device","metrics":{"SI-SDRi":"13.3"},"code_links":[{"title":"wanganran/HybridBeam","url":"https://github.com/wanganran/HybridBeam"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/real-time-directional-hearing-on-vctk","task":"Real-time Directional Hearing","dataset_variant":"VCTK","rows":1,"metrics":["SI-SDRi"],"first_row_in_archive_order":{"model":"HybridBeam+","paper":"/paper/hybrid-neural-networks-for-on-device","metrics":{"SI-SDRi":"13.3"},"code_links":[{"title":"wanganran/HybridBeam","url":"https://github.com/wanganran/HybridBeam"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/voice-conversion-on-vctk","task":"Voice Conversion","dataset_variant":"VCTK","rows":1,"metrics":["Total Length Error (TLE)","Word Length Error (WLE)","Phone Length Error (PLE)"],"first_row_in_archive_order":{"model":"DISSC","paper":"/paper/speaking-style-conversion-with-discrete-self","metrics":{"Phone Length Error (PLE)":"0.023","Total Length Error (TLE)":"0.832","Word Length Error (WLE)":"0.056"},"code_links":[{"title":"gallilmaimon/DISSC","url":"https://github.com/gallilmaimon/DISSC"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/speaking-style-conversion-with-discrete-self","title":"Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units","date":"2022-12-19","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":3,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/aero-audio-super-resolution-in-the-spectral","title":"AERO: Audio Super Resolution in the Spectral Domain","date":"2022-11-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":0,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cmgan-conformer-based-metric-gan-for-monaural","title":"CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement","date":"2022-09-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/neural-vocoder-is-all-you-need-for-speech","title":"Neural Vocoder is All You Need for Speech Super-resolution","date":"2022-03-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hybrid-neural-networks-for-on-device","title":"Hybrid Neural Networks for On-device Directional Hearing","date":"2021-12-11","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tunet-a-block-online-bandwidth-extension","title":"TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining","date":"2021-10-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/self-attention-for-audio-super-resolution","title":"Self-Attention for Audio Super-Resolution","date":"2021-08-26","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/temporal-film-capturing-long-range-sequence-1","title":"Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations.","date":"2019-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/temporal-film-capturing-long-range-sequence","title":"Temporal FiLM: Capturing Long-Range Sequence Dependencies with Feature-Wise Modulations","date":"2019-09-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/audio-super-resolution-using-neural-networks","title":"Audio Super Resolution using Neural Networks","date":"2017-08-02","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":19,"samples_ran":7,"samples_unverified":12,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":1,"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."}