{"url":"/dataset/aishell-3","name":"AISHELL-3","full_name":null,"description_markdown":"AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpus which could be used to train multi-speaker Text-to-Speech (TTS) systems. The corpus contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers and total 88035 utterances. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Accordingly, transcripts in Chinese character-level and pinyin-level are provided along with the recordings. The  word & tone transcription accuracy rate is above 98%, through professional speech annotation and strict quality inspection for tone and prosody.","description_withheld":null,"homepage":"http://www.aishelltech.com/aishell_3","introduced_date":"2020-10-22","introduced_date_note":null,"introduced_by":{"paper":null,"title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines","first_author":null,"url":null},"license":{"name":"Custom (non-commercial)","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Mandarin Chinese","url":"/datasets/language/mandarin-chinese"}],"variants":["AISHELL-3"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/shenberg1/aishell3","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":38,"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":"2026-09-25T09:33:49+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."}