{"id":"https://openalex.org/W3163132306","doi":"https://doi.org/10.1109/icassp39728.2021.9414423","title":"Didispeech: A Large Scale Mandarin Speech Corpus","display_name":"Didispeech: A Large Scale Mandarin Speech Corpus","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163132306","doi":"https://doi.org/10.1109/icassp39728.2021.9414423","mag":"3163132306"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102944502","display_name":"Tingwei Guo","orcid":"https://orcid.org/0000-0002-9320-543X"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingwei Guo","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101966238","display_name":"Wen Cheng","orcid":"https://orcid.org/0000-0002-5585-4957"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Wen","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110582135","display_name":"Dongwei Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongwei Jiang","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049649860","display_name":"Ne Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ne Luo","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029228290","display_name":"Ruixiong Zhang","orcid":"https://orcid.org/0000-0002-8597-8969"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruixiong Zhang","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041886705","display_name":"Shuaijiang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaijiang Zhao","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050050390","display_name":"Wubo Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wubo Li","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107748760","display_name":"Gong Cheng","orcid":"https://orcid.org/0009-0004-0272-3541"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108286207","display_name":"Wei Zou","orcid":"https://orcid.org/0000-0003-4215-5361"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zou","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924647","display_name":"Kun Han","orcid":"https://orcid.org/0000-0003-2148-7594"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Han","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I4401726870","display_name":"Didi Chuxing (China)","ror":"https://ror.org/02ksqcf75","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726870"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["DiDi Chuxing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DiDi Chuxing, Beijing, China","institution_ids":["https://openalex.org/I4401726870"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2184,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9309285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6968","last_page":"6972"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.817573606967926},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7581348419189453},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.7112064957618713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7076117396354675},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5690038800239563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5639059543609619},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.5357562303543091},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5253512263298035},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46443256735801697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.448871910572052},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.43166583776474},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4181499183177948},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16675013303756714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817573606967926},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7581348419189453},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.7112064957618713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7076117396354675},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5690038800239563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5639059543609619},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.5357562303543091},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5253512263298035},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46443256735801697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448871910572052},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.43166583776474},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4181499183177948},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16675013303756714},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1526236009","https://openalex.org/W2039057510","https://openalex.org/W2059673175","https://openalex.org/W2065361420","https://openalex.org/W2113528982","https://openalex.org/W2160815625","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2284628133","https://openalex.org/W2295001676","https://openalex.org/W2327501763","https://openalex.org/W2471520273","https://openalex.org/W2526425061","https://openalex.org/W2625297138","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2890964092","https://openalex.org/W2946200149","https://openalex.org/W2963035245","https://openalex.org/W2963242190","https://openalex.org/W2963403868","https://openalex.org/W2963432880","https://openalex.org/W2963939538","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2971753973","https://openalex.org/W2972359262","https://openalex.org/W2972667718","https://openalex.org/W2981087920","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2998572311","https://openalex.org/W3026957705","https://openalex.org/W3046125265","https://openalex.org/W3095070844","https://openalex.org/W3144035034","https://openalex.org/W3160016036","https://openalex.org/W3160345865","https://openalex.org/W4234330420","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631545277","https://openalex.org/W6695553435","https://openalex.org/W6697498398","https://openalex.org/W6739901393","https://openalex.org/W6752888775","https://openalex.org/W6763832098","https://openalex.org/W6767453231","https://openalex.org/W6769238691","https://openalex.org/W6772349387","https://openalex.org/W6776594914","https://openalex.org/W6777859476","https://openalex.org/W6781268326"],"related_works":["https://openalex.org/W2036933852","https://openalex.org/W4200068392","https://openalex.org/W596245619","https://openalex.org/W2537969829","https://openalex.org/W2550171623","https://openalex.org/W2500421879","https://openalex.org/W2184371793","https://openalex.org/W2186688931","https://openalex.org/W134179020","https://openalex.org/W2014684632"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3],"new":[4],"open-sourced":[5],"Mandarin":[6],"speech":[7,18,32,47,58,65],"corpus,":[8],"called":[9],"DiDiSpeech.":[10],"It":[11],"consists":[12],"of":[13,17],"about":[14],"800":[15],"hours":[16],"data":[19,33],"at":[20,91],"48kHz":[21],"sampling":[22],"rate":[23],"from":[24],"6000":[25],"speakers":[26],"and":[27,42,56,67,84],"the":[28,35,69,78],"corresponding":[29],"texts.":[30],"All":[31],"in":[34,39],"corpus":[36,79,88],"is":[37,43,74,89],"recorded":[38],"quiet":[40],"environment":[41],"suitable":[44],"for":[45,80],"various":[46],"processing":[48],"tasks,":[49],"such":[50],"as":[51],"voice":[52],"conversion,":[53],"multi-speaker":[54],"text-to-speech":[55],"automatic":[57],"recognition.":[59],"We":[60],"conduct":[61],"experiments":[62],"with":[63],"multiple":[64],"tasks":[66],"evaluate":[68],"performance,":[70],"showing":[71],"that":[72],"it":[73],"promising":[75],"to":[76],"use":[77],"both":[81],"academic":[82],"research":[83],"practical":[85],"application.":[86],"The":[87],"available":[90],"https://outreach.didichuxing.com/research/opendata/.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
