{"id":"https://openalex.org/W2799076474","doi":"https://doi.org/10.1109/acssc.2017.8335558","title":"Mismatched crowdsourcing: Mining latent skills to acquire speech transcriptions","display_name":"Mismatched crowdsourcing: Mining latent skills to acquire speech transcriptions","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2799076474","doi":"https://doi.org/10.1109/acssc.2017.8335558","mag":"2799076474"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2017.8335558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2017.8335558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 51st Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["IIT Bombay, Mumbai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037687318","display_name":"Wenda Chen","orcid":"https://orcid.org/0000-0002-6827-9226"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I4210161496","display_name":"A*STAR Graduate Academy","ror":"https://ror.org/059yjzn93","country_code":"SG","type":"education","lineage":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenda Chen","raw_affiliation_strings":["I2R, A∗STAR, Singapore","I2 R, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"I2R, A∗STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I4210161496"]},{"raw_affiliation_string":"I2 R, A*STAR, Singapore","institution_ids":["https://openalex.org/I4210161496"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051897589","display_name":"Van Hai","orcid":"https://orcid.org/0000-0002-9554-5171"},"institutions":[{"id":"https://openalex.org/I182526193","display_name":"Thuyloi University","ror":"https://ror.org/04afshy24","country_code":"VN","type":"education","lineage":["https://openalex.org/I182526193"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van Hai Do","raw_affiliation_strings":["Thuyloi University, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Thuyloi University, Vietnam","institution_ids":["https://openalex.org/I182526193"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"1277","last_page":"1281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.7449613809585571},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6561067700386047},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"Crowdsourcing","score":0.6417324542999268},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5879608988761902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.570060670375824},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5253055691719055},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5084558725357056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4796888530254364},{"id":"https://openalex.org/keywords/zulu","display_name":"Zulu","score":0.46389392018318176},{"id":"https://openalex.org/keywords/first-language","display_name":"First language","score":0.4453563988208771},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.42862948775291443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449613809585571},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6561067700386047},{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.6417324542999268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5879608988761902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.570060670375824},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5253055691719055},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5084558725357056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4796888530254364},{"id":"https://openalex.org/C2778105672","wikidata":"https://www.wikidata.org/wiki/Q10179","display_name":"Zulu","level":2,"score":0.46389392018318176},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.4453563988208771},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42862948775291443},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"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/acssc.2017.8335558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2017.8335558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 51st Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8700000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1436754857","https://openalex.org/W1970533835","https://openalex.org/W2077574412","https://openalex.org/W2142775654","https://openalex.org/W2154095608","https://openalex.org/W2212120078","https://openalex.org/W2513516901","https://openalex.org/W2524233457","https://openalex.org/W2545319977","https://openalex.org/W2547138517","https://openalex.org/W2773389940","https://openalex.org/W4238515972","https://openalex.org/W4285719527","https://openalex.org/W4385773817","https://openalex.org/W6727135808"],"related_works":["https://openalex.org/W1863852300","https://openalex.org/W2121631514","https://openalex.org/W3032998312","https://openalex.org/W135177976","https://openalex.org/W4384486036","https://openalex.org/W1503094549","https://openalex.org/W2337920774","https://openalex.org/W4286908577","https://openalex.org/W2886410948","https://openalex.org/W2015338190"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,66],"recognition":[2],"(ASR)":[3],"converts":[4],"audio":[5,20],"to":[6,32,77,96,155,202],"text.":[7],"ASR":[8],"is":[9,30,70],"usually":[10],"trained":[11],"using":[12,135],"a":[13,85,141],"large":[14],"quantity":[15],"of":[16,84,100,161,167,216],"labeled":[17],"data,":[18],"i.e.,":[19],"with":[21,164],"text":[22,28],"transcription.":[23],"In":[24],"many":[25],"languages,":[26],"however,":[27],"transcription":[29],"hard":[31],"find,":[33],"e.g.,":[34],"in":[35,51,61,67,140,173,193],"both":[36],"Hokkien":[37],"and":[38,55,75],"Dinka,":[39],"we":[40,183],"found":[41],"native":[42,168,188,205],"speakers":[43],"who":[44,56],"had":[45,58],"received":[46],"all":[47],"their":[48,62],"primary":[49],"education":[50],"some":[52,98],"other":[53,180],"language,":[54],"therefore":[57,94],"difficulty":[59],"writing":[60],"own":[63],"language.":[64],"Fortunately,":[65],"every":[68],"language":[69,87,104],"produced":[71],"by":[72,80],"human":[73,81],"mouths,":[74],"designed":[76],"be":[78,153,200],"interpreted":[79],"ears.":[82],"Speakers":[83],"majority":[86],"(English,":[88],"say,":[89,106],"or":[90,107,195],"Mandarin":[91],"Chinese)":[92],"are":[93,111],"able":[95],"make":[97],"sense":[99],"even":[101,185],"the":[102,124,146,179,187,204,212,217],"strangest":[103],"(Zulu,":[105],"Cantonese):":[108],"language-unique":[109],"distinctions":[110,116],"mostly":[112],"lost,":[113],"but":[114],"universal":[115],"such":[117,132],"as":[118],"consonant":[119],"versus":[120],"vowel":[121],"are,":[122],"for":[123],"most":[125],"part,":[126],"correctly":[127],"transmitted.":[128],"We":[129],"can":[130,152,199],"decode":[131],"mismatched":[133,162,191],"transcripts":[134,151,163,192],"an":[136],"information-theoretic":[137],"decoder,":[138],"resulting":[139],"low-entropy":[142],"probability":[143],"distribution":[144],"over":[145],"possible":[147],"native-language":[148],"transcriptions.":[149],"Mismatched":[150],"used":[154,201],"train":[156],"ASR.":[157],"Combining":[158],"ten":[159],"hours":[160],"12\u201348":[165],"minutes":[166],"transcripts,":[169],"if":[170,182],"available,":[171],"results":[172],"lower":[174],"phone":[175],"error":[176],"rate.":[177],"On":[178],"hand,":[181],"don't":[184],"know":[186],"phoneme":[189,206],"inventory,":[190],"two":[194],"more":[196],"annotation":[197,218],"languages":[198],"infer":[203],"inventory":[207,215],"(with":[208],"entropy":[209],"depending":[210],"on":[211],"distinctive":[213],"feature":[214],"languages).":[219]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}