{"id":"https://openalex.org/W2971041032","doi":"https://doi.org/10.1109/taslp.2019.2937953","title":"Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling","display_name":"Exploiting Cross-Lingual Speaker and Phonetic Diversity for Unsupervised Subword Modeling","publication_year":2019,"publication_date":"2019-08-28","ids":{"openalex":"https://openalex.org/W2971041032","doi":"https://doi.org/10.1109/taslp.2019.2937953","mag":"2971041032"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2937953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2937953","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1908.03538","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2531-8480","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.9868,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82296678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":"12","first_page":"2000","last_page":"2011"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9164000153541565,"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":0.9164000153541565,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.008999999612569809,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.005900000222027302,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/frame","display_name":"Frame (networking)","score":0.5796999931335449},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5105000138282776},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.48820000886917114},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.39890000224113464},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3978999853134155},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.3465000092983246},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.34220001101493835},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.33480000495910645},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3287000060081482}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287000060081482},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6723999977111816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6270999908447266},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32010000944137573},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30140000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2019.2937953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2937953","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"},{"id":"pmh:oai:arXiv.org:1908.03538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03538","pdf_url":"https://arxiv.org/pdf/1908.03538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1908.03538","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.03538","pdf_url":"https://arxiv.org/pdf/1908.03538","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W162588823","https://openalex.org/W1528778941","https://openalex.org/W1545920196","https://openalex.org/W1975728937","https://openalex.org/W2005708641","https://openalex.org/W2055408826","https://openalex.org/W2057653135","https://openalex.org/W2072563337","https://openalex.org/W2120209245","https://openalex.org/W2160815625","https://openalex.org/W2167845555","https://openalex.org/W2295297373","https://openalex.org/W2345811097","https://openalex.org/W2400549570","https://openalex.org/W2509930204","https://openalex.org/W2513125788","https://openalex.org/W2514600732","https://openalex.org/W2586754519","https://openalex.org/W2594951208","https://openalex.org/W2614542633","https://openalex.org/W2627092829","https://openalex.org/W2747192917","https://openalex.org/W2759889345","https://openalex.org/W2767122664","https://openalex.org/W2785415724","https://openalex.org/W2785860501","https://openalex.org/W2786902352","https://openalex.org/W2787223168","https://openalex.org/W2787447541","https://openalex.org/W2810166208","https://openalex.org/W2826003142","https://openalex.org/W2889228998","https://openalex.org/W2895297209","https://openalex.org/W2921843068","https://openalex.org/W2963266252","https://openalex.org/W2963620343","https://openalex.org/W3100270690","https://openalex.org/W4239943352","https://openalex.org/W6631362777","https://openalex.org/W6638159135","https://openalex.org/W6640777149","https://openalex.org/W6640828828","https://openalex.org/W6677154653","https://openalex.org/W6677803786","https://openalex.org/W6678947187","https://openalex.org/W6696934422","https://openalex.org/W6712553779","https://openalex.org/W6748325621","https://openalex.org/W6786045457","https://openalex.org/W6973666849"],"related_works":[],"abstract_inverted_index":{"This":[0],"research":[1],"addresses":[2],"the":[3,63,129,135,174,185,211,221,230,245],"problem":[4],"of":[5,8,45,56,62,87,128,168,177,184,200,232,247],"acoustic":[6],"modeling":[7,180],"low-resource":[9],"languages":[10,225,228,239],"for":[11,73,141,236],"which":[12,207],"transcribed":[13,97],"training":[14,75,126,136,234],"data":[15,76,99,127,235],"is":[16,20,66,83,145,196,208],"absent.":[17],"The":[18,38,165,189],"goal":[19],"to":[21,31,68,77,120,133,210],"learn":[22],"robust":[23,88],"frame-level":[24,139],"feature":[25,40,169],"representations":[26,41,90],"that":[27,50,85,148,220],"can":[28,91,117,152],"be":[29,92,118,153],"used":[30],"identify":[32],"and":[33,100,132,226,229],"distinguish":[34],"subword-level":[35],"speech":[36,98,103,137,160],"units.":[37],"proposed":[39,166],"comprise":[42],"various":[43],"types":[44],"multilingual":[46],"bottleneck":[47],"features":[48],"(BNFs)":[49],"are":[51,171],"obtained":[52],"via":[53],"multi-task":[54],"learning":[55,86,170],"deep":[57],"neural":[58],"networks":[59],"(MTL-DNN).":[60],"One":[61],"key":[64],"problems":[65],"how":[67],"acquire":[69],"high-quality":[70],"frame":[71,150,163],"labels":[72,140,151],"untranscribed":[74,125],"facilitate":[78],"supervised":[79],"DNN":[80,142],"training.":[81,143],"It":[82,144],"shown":[84],"BNF":[89],"achieved":[93,192],"by":[94,155,193],"effectively":[95],"leveraging":[96],"well-trained":[101],"automatic":[102],"recognition":[104],"(ASR)":[105],"systems":[106,116,213],"from":[107],"one":[108],"or":[109],"more":[110],"out-of-domain":[111,227],"(resource-rich)":[112],"languages.":[113],"Out-of-domain":[114],"ASR":[115],"applied":[119],"perform":[121],"speaker":[122],"adaptation":[123],"with":[124],"target":[130,224,238],"language,":[131],"decode":[134],"into":[138],"also":[146],"found":[147],"better":[149],"generated":[154],"considering":[156],"temporal":[157],"dependency":[158],"in":[159,181,198],"when":[161],"performing":[162],"clustering.":[164],"methods":[167],"evaluated":[172],"on":[173,244],"standard":[175],"task":[176],"unsupervised":[178],"subword":[179],"Track":[182],"1":[183],"ZeroSpeech":[186],"2017":[187],"Challenge.":[188],"best":[190,212],"performance":[191],"our":[194,217],"system":[195],"9.7%":[197],"terms":[199],"across-speaker":[201],"triphone":[202],"minimal-pair":[203],"ABX":[204],"error":[205],"rate,":[206],"comparable":[209],"reported":[214],"recently.":[215],"Lastly,":[216],"investigation":[218],"reveals":[219],"closeness":[222],"between":[223],"amount":[231],"available":[233],"individual":[237],"could":[240],"have":[241],"significant":[242],"impact":[243],"goodness":[246],"learned":[248],"features.":[249]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-09-05T00:00:00"}