{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/aishell-1-an-open-source-mandarin-speech","title":"AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline","arxiv_id":"1709.05522","date":"2017-09-16","proceeding":null,"authors":["Hui Bu","Jiayu Du","Xingyu Na","Bengu Wu","Hao Zheng"],"abstract":"An open-source Mandarin speech corpus called AISHELL-1 is released. It is by\nfar the largest corpus which is suitable for conducting the speech recognition\nresearch and building speech recognition systems for Mandarin. The recording\nprocedure, including audio capturing devices and environments are presented in\ndetails. The preparation of the related resources, including transcriptions and\nlexicon are described. The corpus is released with a Kaldi recipe. Experimental\nresults implies that the quality of audio recordings and transcriptions are\npromising.","url_abs":"http://arxiv.org/abs/1709.05522v1","url_pdf":"http://arxiv.org/pdf/1709.05522v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"aishell-1-an-open-source-mandarin-speech","repo_url":"https://github.com/jyhan03/icassp22-dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"aishell-1-an-open-source-mandarin-speech","repo_url":"https://github.com/PaddlePaddle/PaddleSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[{"slug":"aishell-1","name":"AISHELL-1","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.05522","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}