{"id":"https://openalex.org/W2808291730","doi":"https://doi.org/10.1109/icsda.2017.8384463","title":"Chinese TIMIT: A TIMIT-like corpus of standard Chinese","display_name":"Chinese TIMIT: A TIMIT-like corpus of standard Chinese","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2808291730","doi":"https://doi.org/10.1109/icsda.2017.8384463","mag":"2808291730"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2017.8384463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384463","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/A5043406907","display_name":"Jiahong Yuan","orcid":"https://orcid.org/0009-0008-2162-7167"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiahong Yuan","raw_affiliation_strings":["Linauistic Data Consortium, University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Linauistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040214647","display_name":"Hongwei Ding","orcid":"https://orcid.org/0000-0001-8684-0788"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Ding","raw_affiliation_strings":["Institute of Cross-Linguistic Processing and Cognition, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Cross-Linguistic Processing and Cognition, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079951703","display_name":"Sishi Liao","orcid":"https://orcid.org/0000-0002-9420-1377"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sishi Liao","raw_affiliation_strings":["Institute of Cross-Linguistic Processing and Cognition, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Cross-Linguistic Processing and Cognition, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101037586","display_name":"Yuqing Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqing Zhan","raw_affiliation_strings":["Institute of Cross-Linguistic Processing and Cognition, Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Institute of Cross-Linguistic Processing and Cognition, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["Linauistic Data Consortium, University of Pennsylvania"],"affiliations":[{"raw_affiliation_string":"Linauistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043406907"],"corresponding_institution_ids":["https://openalex.org/I4210120198"],"apc_list":null,"apc_paid":null,"fwci":0.4157,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.74810201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.9678295254707336},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486815452575684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7175939679145813},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7035922408103943},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6977818608283997},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6021772027015686},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5300217270851135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49028804898262024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48192644119262695},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.19950178265571594},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.15657976269721985},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15040135383605957}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.9678295254707336},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486815452575684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7175939679145813},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7035922408103943},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6977818608283997},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6021772027015686},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5300217270851135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49028804898262024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48192644119262695},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.19950178265571594},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.15657976269721985},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15040135383605957},{"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/icsda.2017.8384463","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2017.8384463","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W117714366","https://openalex.org/W121610373","https://openalex.org/W289577468","https://openalex.org/W1996580912","https://openalex.org/W2045956438","https://openalex.org/W2143996311","https://openalex.org/W2401167848","https://openalex.org/W2401693139","https://openalex.org/W2498935864","https://openalex.org/W3127686677","https://openalex.org/W4285719527","https://openalex.org/W6603616073","https://openalex.org/W6604720443","https://openalex.org/W6605039604","https://openalex.org/W6610453334"],"related_works":["https://openalex.org/W36113703","https://openalex.org/W3127686677","https://openalex.org/W2038050265","https://openalex.org/W80423236","https://openalex.org/W2808291730","https://openalex.org/W2140130847","https://openalex.org/W2397167112","https://openalex.org/W3012168345","https://openalex.org/W1961523962","https://openalex.org/W2056168066"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"effort":[4],"to":[5,74],"build":[6],"a":[7],"TIMIT-like":[8],"corpus":[9,41,97],"in":[10,27,95,117],"Standard":[11],"Chinese,":[12],"which":[13,63],"is":[14,61],"part":[15],"of":[16,31,43,86,91],"our":[17],"\"Global":[18],"TIMIT\"":[19],"project.":[20],"Three":[21],"steps":[22],"are":[23,98],"involved":[24],"and":[25,35,37,52,88,93,107,126],"detailed":[26],"the":[28,84,96],"paper:":[29],"selection":[30],"sentences;":[32],"speaker":[33],"recruitment":[34],"recording;":[36],"phonetic":[38],"segmentation.":[39],"The":[40],"consists":[42],"6000":[44],"sentences":[45],"read":[46],"by":[47],"50":[48,78],"speakers":[49],"(25":[50],"females":[51],"25":[53],"males).":[54],"Phonetic":[55],"segmentation":[56,76],"obtained":[57],"from":[58],"forced":[59],"alignment":[60],"provided,":[62],"has":[64],"93.2%":[65],"agreement":[66],"(of":[67],"phone":[68],"boundaries)":[69],"within":[70],"20":[71],"ms":[72],"compared":[73],"manual":[75],"on":[77,83],"randomly":[79],"selected":[80],"sentences.":[81],"Statistics":[82],"number":[85],"tokens":[87],"mean":[89],"duration":[90],"phones":[92],"tones":[94],"also":[99],"reported.":[100],"Males":[101],"have":[102],"shorter":[103],"phones/tones":[104],"but":[105,122],"more":[106,124],"longer":[108],"utterance":[109],"internal":[110],"silences":[111],"than":[112],"females,":[113],"demonstrating":[114],"that":[115],"males":[116],"this":[118],"dataset":[119],"speak":[120],"faster":[121],"pause":[123],"frequently":[125],"longer.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}