{"id":"https://openalex.org/W4285821318","doi":"https://doi.org/10.1109/jstsp.2022.3191845","title":"Self-Supervised Learning With Segmental Masking for Speech Representation","display_name":"Self-Supervised Learning With Segmental Masking for Speech Representation","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4285821318","doi":"https://doi.org/10.1109/jstsp.2022.3191845"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3191845","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3191845","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09832492.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09832492.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060201191","display_name":"Xianghu Yue","orcid":"https://orcid.org/0000-0003-3527-6034"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xianghu Yue","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3527-6034","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108668360","display_name":"Jingru Lin","orcid":"https://orcid.org/0009-0001-9367-7672"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingru Lin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044459608","display_name":"Fabian Ritter Gutierrez","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fabian Ritter Gutierrez","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","Kriston AI, Xiamen, China","Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Kriston AI, Xiamen, China","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5060201191"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.526,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8531356,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"16","issue":"6","first_page":"1367","last_page":"1379"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9986000061035156,"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":0.9980000257492065,"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/masking","display_name":"Masking (illustration)","score":0.8612082004547119},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8104317784309387},{"id":"https://openalex.org/keywords/phonotactics","display_name":"Phonotactics","score":0.7770833969116211},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.709762454032898},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5715615749359131},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5011312961578369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4855318069458008},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4541773200035095},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42686864733695984},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4146576523780823},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.21563544869422913},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10326045751571655}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.8612082004547119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104317784309387},{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.7770833969116211},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.709762454032898},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5715615749359131},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5011312961578369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4855318069458008},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4541773200035095},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42686864733695984},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4146576523780823},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.21563544869422913},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10326045751571655},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/jstsp.2022.3191845","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3191845","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09832492.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/jstsp.2022.3191845","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3191845","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09832492.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G861645084","display_name":null,"funder_award_id":"B10120210117-KP02","funder_id":"https://openalex.org/F4320322942","funder_display_name":"Chinese University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285821318.pdf","grobid_xml":"https://content.openalex.org/works/W4285821318.grobid-xml"},"referenced_works_count":82,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1934184906","https://openalex.org/W1995562189","https://openalex.org/W2002342963","https://openalex.org/W2024490156","https://openalex.org/W2041394569","https://openalex.org/W2056407084","https://openalex.org/W2077804127","https://openalex.org/W2105482032","https://openalex.org/W2125496931","https://openalex.org/W2143612262","https://openalex.org/W2146334809","https://openalex.org/W2155721440","https://openalex.org/W2157331557","https://openalex.org/W2514741789","https://openalex.org/W2747874407","https://openalex.org/W2766219058","https://openalex.org/W2794209590","https://openalex.org/W2808682925","https://openalex.org/W2962739339","https://openalex.org/W2962799131","https://openalex.org/W2962901777","https://openalex.org/W2964227577","https://openalex.org/W2965373594","https://openalex.org/W2972584841","https://openalex.org/W2972943112","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2981087920","https://openalex.org/W2981991061","https://openalex.org/W2982223350","https://openalex.org/W2987283559","https://openalex.org/W3006094508","https://openalex.org/W3007552021","https://openalex.org/W3011411500","https://openalex.org/W3015213852","https://openalex.org/W3015265920","https://openalex.org/W3016011332","https://openalex.org/W3016181583","https://openalex.org/W3026842484","https://openalex.org/W3035202887","https://openalex.org/W3035725276","https://openalex.org/W3041561163","https://openalex.org/W3049256661","https://openalex.org/W3096485810","https://openalex.org/W3096656254","https://openalex.org/W3097286738","https://openalex.org/W3097787369","https://openalex.org/W3100270690","https://openalex.org/W3102342027","https://openalex.org/W3104896896","https://openalex.org/W3148040514","https://openalex.org/W3160345865","https://openalex.org/W3162133897","https://openalex.org/W3196919915","https://openalex.org/W3197227964","https://openalex.org/W3197580070","https://openalex.org/W3197974236","https://openalex.org/W3198771897","https://openalex.org/W3198782837","https://openalex.org/W3209059054","https://openalex.org/W3209993061","https://openalex.org/W4226033575","https://openalex.org/W4297808394","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6766673545","https://openalex.org/W6768021236","https://openalex.org/W6769196770","https://openalex.org/W6769238691","https://openalex.org/W6771467084","https://openalex.org/W6774314701","https://openalex.org/W6778265221","https://openalex.org/W6779216093","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6795952400","https://openalex.org/W6844194202","https://openalex.org/W6864750640"],"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/W4389100922","https://openalex.org/W1602082497","https://openalex.org/W2975191379","https://openalex.org/W2118180989"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,7,23],"has":[2],"achieved":[3],"remarkable":[4],"success":[5],"for":[6],"speech":[8,74,92,170],"representations":[9],"from":[10],"unlabeled":[11],"data.":[12],"The":[13],"masking":[14,28,49,85,134,140,150,167],"strategy":[15,135,168],"plays":[16],"an":[17,100,163],"important":[18,164],"role":[19],"in":[20,99,169],"the":[21,27,39,60,72,96,108,124,132,138,146],"self-supervised":[22],"algorithm.":[24],"Most":[25],"of":[26,42,65,110,120,148],"techniques":[29],"operate":[30],"at":[31,53],"a":[32,48,54,66,82,111],"frame":[33],"level.":[34],"In":[35,77],"linguistics,":[36],"phone":[37],"is":[38],"smallest":[40],"unit":[41,151],"sound.":[43],"Hence,":[44],"we":[45,80,88,105,129],"believe":[46],"that":[47,51,131],"technique":[50],"operates":[52],"phoneme":[55,155],"level":[56],"will":[57],"effectively":[58],"encode":[59],"phonotactic":[61,116],"and":[62,118,157],"prosodic":[63],"constraints":[64,117],"spoken":[67,112],"language,":[68,113],"thus":[69],"eventually":[70],"benefits":[71],"downstream":[73],"recognition":[75],"tasks.":[76],"this":[78],"work,":[79],"explore":[81],"novel":[83],"segmental":[84,133,149],"strategy.":[86],"Specifically,":[87],"mask":[89],"phonetically":[90],"motivated":[91],"segments":[93],"according":[94],"to":[95],"phonetic":[97,121],"segmentation":[98],"utterance.":[101],"By":[102],"doing":[103],"so,":[104],"implicitly":[106],"incorporate":[107],"properties":[109],"such":[114],"as":[115],"duration":[119],"segments,":[122],"into":[123],"pre-training.":[125],"Through":[126],"extensive":[127],"experiments,":[128],"confirm":[130],"consistently":[136],"outperforms":[137],"frame-based":[139],"counterpart.":[141],"We":[142],"also":[143],"further":[144],"investigate":[145],"effect":[147],"size,":[152],"i.e.":[153],"phoneme,":[154],"span,":[156],"lexical":[158],"word.":[159],"This":[160],"work":[161],"presents":[162],"finding":[165],"about":[166],"representation":[171],"learning.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}