{"id":"https://openalex.org/W2963242190","doi":"https://doi.org/10.1109/icsda.2017.8384449","title":"AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline","display_name":"AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2963242190","doi":"https://doi.org/10.1109/icsda.2017.8384449","mag":"2963242190"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0002-5883-1195"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hui Bu","raw_affiliation_strings":["Beijing Shell Shell Technology Co. Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Shell Shell Technology Co. Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025820127","display_name":"Jiayu Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayu Du","raw_affiliation_strings":["Independent Researcher*, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher*, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012173647","display_name":"Xingyu Na","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Na","raw_affiliation_strings":["Independent Researcher*, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher*, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054308128","display_name":"Bengu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bengu Wu","raw_affiliation_strings":["Independent Researcher*, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher*, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101981249","display_name":"Hao Zheng","orcid":"https://orcid.org/0000-0003-3615-7440"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zheng","raw_affiliation_strings":["Independent Researcher*, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Independent Researcher*, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101791717"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.874,"has_fulltext":false,"cited_by_count":769,"citation_normalized_percentile":{"value":0.99672774,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8841853737831116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.793877124786377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7537887692451477},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6636872291564941},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.6587862968444824},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5950870513916016},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5788278579711914},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4546317756175995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4461002051830292},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4184415936470032},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4119587242603302},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3640965521335602},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16828513145446777}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8841853737831116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793877124786377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7537887692451477},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6636872291564941},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.6587862968444824},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5950870513916016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5788278579711914},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4546317756175995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4461002051830292},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4184415936470032},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4119587242603302},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3640965521335602},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16828513145446777},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2017.8384449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 20th Conference of the Oriental Chapter of the International Coordinating Committee on Speech Databases and Speech I/O Systems and Assessment (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1762484328","https://openalex.org/W1922655562","https://openalex.org/W2035424729","https://openalex.org/W2085628288","https://openalex.org/W2160815625","https://openalex.org/W2164240571","https://openalex.org/W2250357346","https://openalex.org/W2284628133","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W6637956674","https://openalex.org/W6640090968","https://openalex.org/W6712930963","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W4397292310","https://openalex.org/W4200068392","https://openalex.org/W2184371793","https://openalex.org/W2537969829","https://openalex.org/W596245619","https://openalex.org/W4388404911","https://openalex.org/W4312742405","https://openalex.org/W2105439218","https://openalex.org/W2066051122","https://openalex.org/W2147998355"],"abstract_inverted_index":{"An":[0],"open-source":[1],"Mandarin":[2],"speech":[3,22,27],"corpus":[4,15,58],"called":[5],"AISHELL-1":[6],"is":[7,10,17,59],"released.":[8],"It":[9],"by":[11],"far":[12],"the":[13,21,48,69],"largest":[14],"which":[16],"suitable":[18],"for":[19,30],"conducting":[20],"recognition":[23,28],"research":[24],"and":[25,39,53,74],"building":[26],"systems":[29],"Mandarin.":[31],"The":[32,45,57],"recording":[33],"procedure,":[34],"including":[35,51],"audio":[36,72],"capturing":[37],"devices":[38],"environments":[40],"are":[41,55,76],"presented":[42],"in":[43],"details.":[44],"preparation":[46],"of":[47,71],"related":[49],"resources,":[50],"transcriptions":[52,75],"lexicon":[54],"described.":[56],"released":[60],"with":[61],"a":[62],"Kaldi":[63],"recipe.":[64],"Experimental":[65],"results":[66],"implies":[67],"that":[68],"quality":[70],"recordings":[73],"promising.":[77]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":96},{"year":2024,"cited_by_count":120},{"year":2023,"cited_by_count":112},{"year":2022,"cited_by_count":123},{"year":2021,"cited_by_count":168},{"year":2020,"cited_by_count":78},{"year":2019,"cited_by_count":49},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
