{"id":"https://openalex.org/W4205706554","doi":"https://doi.org/10.1109/taslp.2021.3138720","title":"Learning Phone Recognition From Unpaired Audio and Phone Sequences Based on Generative Adversarial Network","display_name":"Learning Phone Recognition From Unpaired Audio and Phone Sequences Based on Generative Adversarial Network","publication_year":2021,"publication_date":"2021-12-28","ids":{"openalex":"https://openalex.org/W4205706554","doi":"https://doi.org/10.1109/taslp.2021.3138720"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3138720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138720","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5084868332","display_name":"Da-Rong Liu","orcid":"https://orcid.org/0009-0005-0090-7408"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-rong Liu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f07942148@ntu.edu.tw)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f07942148@ntu.edu.tw)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034235870","display_name":"Po\u2010Chun Hsu","orcid":"https://orcid.org/0000-0002-6509-9377"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-chun Hsu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f07942095@ntu.edu.tw)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f07942095@ntu.edu.tw)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450914","display_name":"Yi\u2010Chen Chen","orcid":"https://orcid.org/0000-0002-4616-2115"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-chen Chen","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","National Taiwan University, 33561 Taipei, Taiwan, (e-mail: ericwudayi2@gmail.com)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 33561 Taipei, Taiwan, (e-mail: ericwudayi2@gmail.com)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sung-feng Huang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f04942141@ntu.edu.tw)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f04942141@ntu.edu.tw)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028930617","display_name":"Shun-Po Chuang","orcid":"https://orcid.org/0000-0003-0720-2732"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shun-po Chuang","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f06942069@ntu.edu.tw)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f06942069@ntu.edu.tw)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017182348","display_name":"Da-Yi Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Da-yi Wu","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan","National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f06942045@ntu.edu.tw)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, 33561 Taipei, Taiwan, (e-mail: f06942045@ntu.edu.tw)","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-9654-5747","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9795,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81392327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"30","issue":null,"first_page":"230","last_page":"243"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/computer-science","display_name":"Computer science","score":0.7860655784606934},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7514670491218567},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.573701024055481},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5497159361839294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5274184942245483},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5260189175605774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4809214770793915},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46552345156669617},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4254821538925171},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38318297266960144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3326232433319092},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3323051333427429},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.07049661874771118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860655784606934},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7514670491218567},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.573701024055481},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5497159361839294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5274184942245483},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5260189175605774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4809214770793915},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46552345156669617},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4254821538925171},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38318297266960144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3326232433319092},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3323051333427429},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.07049661874771118},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3138720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3138720","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W10548402","https://openalex.org/W130754613","https://openalex.org/W1496120315","https://openalex.org/W1577418252","https://openalex.org/W1606268232","https://openalex.org/W1992613273","https://openalex.org/W2059652594","https://openalex.org/W2099471712","https://openalex.org/W2121997342","https://openalex.org/W2140277151","https://openalex.org/W2190506272","https://openalex.org/W2296681920","https://openalex.org/W2347098582","https://openalex.org/W2531207078","https://openalex.org/W2593011301","https://openalex.org/W2747078529","https://openalex.org/W2786902352","https://openalex.org/W2804648901","https://openalex.org/W2889313720","https://openalex.org/W2899134946","https://openalex.org/W2927191280","https://openalex.org/W2940544976","https://openalex.org/W2962736743","https://openalex.org/W2962799131","https://openalex.org/W2962799225","https://openalex.org/W2962824709","https://openalex.org/W2962980711","https://openalex.org/W2963137467","https://openalex.org/W2963425185","https://openalex.org/W2963571336","https://openalex.org/W2963609956","https://openalex.org/W2963720603","https://openalex.org/W2972574141","https://openalex.org/W2972867623","https://openalex.org/W2973026522","https://openalex.org/W3036601975","https://openalex.org/W3093096176","https://openalex.org/W3095173472","https://openalex.org/W3096656254","https://openalex.org/W3097692357","https://openalex.org/W3097777922","https://openalex.org/W3100270690","https://openalex.org/W3161215977","https://openalex.org/W3198134274","https://openalex.org/W4287173589","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6675022971","https://openalex.org/W6713185182","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6731763572","https://openalex.org/W6735913928","https://openalex.org/W6738077056","https://openalex.org/W6738767006","https://openalex.org/W6739901393","https://openalex.org/W6744957266","https://openalex.org/W6745388339","https://openalex.org/W6745740328","https://openalex.org/W6751433836","https://openalex.org/W6757699909","https://openalex.org/W6760519848","https://openalex.org/W6767164110","https://openalex.org/W6769196770","https://openalex.org/W6779669310","https://openalex.org/W6780218876","https://openalex.org/W6795952400"],"related_works":["https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2153098279","https://openalex.org/W1990589093","https://openalex.org/W3005996785","https://openalex.org/W2501000458","https://openalex.org/W4386984417","https://openalex.org/W1578749070","https://openalex.org/W2476099471","https://openalex.org/W2146842779"],"abstract_inverted_index":{"ASRhas":[0],"been":[1],"shown":[2],"to":[3,29,53,73,107],"achieve":[4],"great":[5],"performance":[6,82],"recently.":[7],"However,":[8],"most":[9],"of":[10,100,110],"them":[11],"rely":[12],"on":[13,146],"massive":[14],"paired":[15],"data,":[16],"which":[17,79],"is":[18,47,71],"not":[19],"feasible":[20],"for":[21,88],"low-resource":[22],"languages":[23],"worldwide.":[24],"This":[25],"paper":[26],"investigates":[27],"how":[28],"learn":[30],"directly":[31],"from":[32,75,124,142],"unpaired":[33,59,125,143],"phone":[34,62],"sequences":[35],"and":[36,61,83,138],"speech":[37,60],"utterances.":[38],"We":[39],"design":[40],"a":[41,85],"two-stage":[42],"iterative":[43],"framework.":[44],"GAN":[45],"training":[46],"adopted":[48],"in":[49],"the":[50,55,65,76,81,89,93,105,147],"first":[51,96],"stage":[52],"find":[54],"mapping":[56],"relationship":[57],"between":[58],"sequence.":[63],"In":[64,92],"second":[66],"stage,":[67],"another":[68],"HMM":[69],"model":[70,101],"introduced":[72],"train":[74],"generator\u2019s":[77],"output,":[78],"boosts":[80],"provides":[84],"better":[86,131],"segmentation":[87],"next":[90],"iteration.":[91],"experiment,":[94],"we":[95],"investigate":[97],"different":[98,108],"choices":[99],"designs.":[102],"Thenwe":[103],"compare":[104],"framework":[106,128],"types":[109],"baselines:":[111],"(i)":[112],"supervised":[113],"methods":[114,120,122,137,140],"(ii)":[115],"acoustic":[116,134],"unit":[117,135],"discovery":[118,136],"based":[119,145],"(iii)":[121],"learning":[123,141],"data.":[126],"Our":[127],"performs":[129],"consistently":[130],"than":[132],"all":[133],"previous":[139],"data":[144],"TIMIT":[148],"dataset.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
