{"id":"https://openalex.org/W4221158519","doi":"https://doi.org/10.21437/interspeech.2022-354","title":"PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification","display_name":"PHO-LID: A Unified Model Incorporating Acoustic-Phonetic and Phonotactic Information for Language Identification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221158519","doi":"https://doi.org/10.21437/interspeech.2022-354"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-354","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-354","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5091096053","display_name":"Hexin Liu","orcid":"https://orcid.org/0000-0002-3998-9229"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hexin Liu","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia Perera","raw_affiliation_strings":["CLSP and HLT-COE, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CLSP and HLT-COE, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010202250","display_name":"Andy W. H. Khong","orcid":"https://orcid.org/0000-0002-0708-4791"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Andy Khong","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072241540","display_name":"Suzy J Styles","orcid":"https://orcid.org/0000-0003-3517-9680"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suzy Styles","raw_affiliation_strings":["Psychology, School of Social Sciences, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Psychology, School of Social Sciences, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["CLSP and HLT-COE, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CLSP and HLT-COE, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091096053"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.1418,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.79374503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2233","last_page":"2237"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9936000108718872,"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/phonotactics","display_name":"Phonotactics","score":0.9670987725257874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8013037443161011},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6323816776275635},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47437411546707153},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44757065176963806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3847019672393799},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20322513580322266},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.168840229511261}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.9670987725257874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013037443161011},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6323816776275635},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47437411546707153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44757065176963806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3847019672393799},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20322513580322266},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.168840229511261},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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:10.21437/interspeech.2022-354","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-354","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G2235879186","display_name":null,"funder_award_id":"NRF2016-SOL002-011","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G277544474","display_name":null,"funder_award_id":"NRF2016","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4267629283","display_name":null,"funder_award_id":"NRF2016-SOL002-011","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G5877145623","display_name":"CCRI: ENS: Next Generation Tools for Spoken Language Science & Technology","funder_award_id":"2120435","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W80991132","https://openalex.org/W97072897","https://openalex.org/W1524333225","https://openalex.org/W1983072039","https://openalex.org/W2104457544","https://openalex.org/W2152790380","https://openalex.org/W2166637769","https://openalex.org/W2172287020","https://openalex.org/W2292087804","https://openalex.org/W2403547305","https://openalex.org/W2408021097","https://openalex.org/W2807627734","https://openalex.org/W2963032538","https://openalex.org/W2963063081","https://openalex.org/W2963307329","https://openalex.org/W2972433488","https://openalex.org/W3010983946","https://openalex.org/W3024182269","https://openalex.org/W3030437843","https://openalex.org/W3036601975","https://openalex.org/W3095410713","https://openalex.org/W3096656254","https://openalex.org/W3198429080","https://openalex.org/W4221147641","https://openalex.org/W4245923654","https://openalex.org/W4287113299","https://openalex.org/W4297808394","https://openalex.org/W4361745846","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2615317726","https://openalex.org/W2021909761","https://openalex.org/W198649858","https://openalex.org/W2467354670","https://openalex.org/W2498910126","https://openalex.org/W2497306275","https://openalex.org/W2619211984","https://openalex.org/W1603786716","https://openalex.org/W2488456180","https://openalex.org/W3192589309"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,26,32,36,123],"novel":[3],"model":[4,96,125],"to":[5,55,122],"hierarchically":[6],"incorporate":[7],"phoneme":[8,18,28,159,169],"and":[9,31,47,83,91,161],"phonotactic":[10],"information":[11,50,170],"for":[12,20,71,128,171],"language":[13,45],"identification":[14],"(LID)":[15],"without":[16],"requiring":[17],"annotations":[19],"training.In":[21],"this":[22,75],"model,":[23],"named":[24],"PHO-LID,":[25],"self-supervised":[27],"segmentation":[29],"task":[30,34],"LID":[33,103],"share":[35],"convolutional":[37],"neural":[38],"network":[39],"(CNN)":[40],"module,":[41],"which":[42],"encodes":[43],"both":[44],"identity":[46],"sequential":[48],"phonemic":[49],"in":[51,113,147],"the":[52,84,94,101,144,153,166],"input":[53],"speech":[54],"generate":[56],"an":[57],"intermediate":[58],"sequence":[59],"of":[60,87,115,143,168],"\"phonotactic\"":[61],"embeddings.These":[62],"embeddings":[63],"are":[64],"then":[65],"fed":[66],"into":[67],"transformer":[68],"encoder":[69],"layers":[70],"utterance-level":[72],"LID.We":[73],"call":[74],"architecture":[76],"CNN-Trans.We":[77],"evaluate":[78],"it":[79],"on":[80,118,141],"AP17-OLR":[81,119],"data":[82,120,151],"MLS14":[85],"set":[86],"NIST":[88,148],"LRE":[89,149],"2017,":[90],"show":[92],"that":[93,134],"PHO-LID":[95],"with":[97],"multitask":[98],"optimization":[99],"exhibits":[100],"highest":[102],"performance":[104,140],"among":[105],"all":[106],"models,":[107],"achieving":[108],"over":[109],"40%":[110],"relative":[111],"improvement":[112],"terms":[114],"average":[116],"cost":[117],"compared":[121],"CNN-Trans":[124,154],"optimized":[126],"only":[127],"LID.The":[129],"visualized":[130],"confusion":[131],"matrices":[132],"imply":[133],"our":[135],"proposed":[136],"method":[137],"achieves":[138],"higher":[139],"languages":[142],"same":[145],"cluster":[146],"2017":[150],"than":[152],"model.A":[155],"comparison":[156],"between":[157],"predicted":[158],"boundaries":[160],"corresponding":[162],"audio":[163],"spectrograms":[164],"illustrates":[165],"leveraging":[167],"LID.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}