{"id":"https://openalex.org/W3204915839","doi":"https://doi.org/10.1109/taslp.2022.3180684","title":"Unsupervised Speech Segmentation and Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding","display_name":"Unsupervised Speech Segmentation and Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3204915839","doi":"https://doi.org/10.1109/taslp.2022.3180684","mag":"3204915839"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3180684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3180684","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/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"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":"Saurabhchand Bhati","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0001-6477-3895","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"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":"Jesus Villalba","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"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":"Piotr Zelasko","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-8245-0413","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069488212","display_name":"Laureano Moro-Vel\u00e1zquez","orcid":"https://orcid.org/0000-0002-3033-7005"},"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":"Laureano Moro-Velazquez","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-3033-7005","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"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":"Najim Dehak","raw_affiliation_strings":["Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-4489-5753","affiliations":[{"raw_affiliation_string":"Center for Language, Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.6687,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90828527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"2002","last_page":"2014"},"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7900184988975525},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6207278370857239},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6154862642288208},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5583999156951904},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5301438570022583},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4510367512702942},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.41705840826034546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3774871230125427},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.08339300751686096}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900184988975525},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6207278370857239},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6154862642288208},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5583999156951904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5301438570022583},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4510367512702942},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.41705840826034546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3774871230125427},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.08339300751686096},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3180684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3180684","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W1525748279","https://openalex.org/W1778492285","https://openalex.org/W1828163288","https://openalex.org/W1994458317","https://openalex.org/W2010188467","https://openalex.org/W2020607164","https://openalex.org/W2057007397","https://openalex.org/W2078769636","https://openalex.org/W2100768664","https://openalex.org/W2111732304","https://openalex.org/W2115197214","https://openalex.org/W2115867364","https://openalex.org/W2117041980","https://openalex.org/W2117126688","https://openalex.org/W2126377586","https://openalex.org/W2127141656","https://openalex.org/W2145410271","https://openalex.org/W2146444479","https://openalex.org/W2150769028","https://openalex.org/W2152790380","https://openalex.org/W2160815625","https://openalex.org/W2170659185","https://openalex.org/W2242818861","https://openalex.org/W2468716020","https://openalex.org/W2478415332","https://openalex.org/W2601836666","https://openalex.org/W2719865699","https://openalex.org/W2747192917","https://openalex.org/W2752796333","https://openalex.org/W2786608204","https://openalex.org/W2842511635","https://openalex.org/W2882319491","https://openalex.org/W2890704021","https://openalex.org/W2890718354","https://openalex.org/W2940544976","https://openalex.org/W2949382160","https://openalex.org/W2962799131","https://openalex.org/W2963137467","https://openalex.org/W2963341956","https://openalex.org/W2963620343","https://openalex.org/W2963799213","https://openalex.org/W2964169922","https://openalex.org/W2965373594","https://openalex.org/W2972794572","https://openalex.org/W2973026522","https://openalex.org/W2973049979","https://openalex.org/W2981857663","https://openalex.org/W2991213871","https://openalex.org/W2996383576","https://openalex.org/W3008499099","https://openalex.org/W3027324582","https://openalex.org/W3034978746","https://openalex.org/W3036601975","https://openalex.org/W3095361818","https://openalex.org/W3096656254","https://openalex.org/W3098643042","https://openalex.org/W3099782249","https://openalex.org/W3100270690","https://openalex.org/W3110458199","https://openalex.org/W3112613336","https://openalex.org/W3125709657","https://openalex.org/W3127686677","https://openalex.org/W3169072315","https://openalex.org/W3198134274","https://openalex.org/W3198782837","https://openalex.org/W4287173589","https://openalex.org/W4301204483","https://openalex.org/W4394671563","https://openalex.org/W6631526040","https://openalex.org/W6638749077","https://openalex.org/W6675022971","https://openalex.org/W6682948231","https://openalex.org/W6690026940","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6769196770","https://openalex.org/W6770506093","https://openalex.org/W6774314701","https://openalex.org/W6774456908","https://openalex.org/W6780218876","https://openalex.org/W6786696081","https://openalex.org/W6789826613","https://openalex.org/W6790356757","https://openalex.org/W6795952400","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2071828724","https://openalex.org/W1669577408","https://openalex.org/W1994694193","https://openalex.org/W2161865195","https://openalex.org/W170831052","https://openalex.org/W4247725880","https://openalex.org/W2978471304","https://openalex.org/W1006721676","https://openalex.org/W2100854157","https://openalex.org/W1771058801"],"abstract_inverted_index":{"Typically,":[0],"unsupervised":[1],"segmentation":[2,172],"of":[3,30,183,265],"speech":[4,237],"into":[5],"the":[6,28,31,69,82,101,119,181,184,197,215,220,228,240,246,263,266,271,276,291,298],"phone-":[7],"and":[8,16,38,157,170,176,190,219,254],"word-like":[9],"units":[10],"are":[11,17,134,227],"treated":[12],"as":[13,63,202,204,281,283,295],"separate":[14],"tasks":[15,51],"often":[18],"done":[19],"via":[20,122,142],"different":[21],"methods":[22,173],"which":[23,133],"do":[24],"not":[25],"fully":[26],"leverage":[27],"inter-dependence":[29],"two":[32,50],"tasks.":[33],"Here,":[34],"we":[35,232],"unify":[36],"them":[37],"propose":[39],"a":[40,92,105,139],"technique":[41],"that":[42,48,163,194,207,211,259],"can":[43,200,269],"jointly":[44],"perform":[45],"both,":[46],"showing":[47],"these":[49],"indeed":[52],"benefit":[53],"from":[54,118,275],"each":[55],"other.":[56],"Recent":[57],"attempts":[58],"employ":[59],"self-supervised":[60],"learning,":[61],"such":[62,294],"contrastive":[64,94],"predictive":[65,95],"coding":[66,96],"(CPC),":[67],"where":[68],"next":[70],"frame":[71,249],"is":[72],"predicted":[73],"given":[74],"past":[75],"context.":[76],"However,":[77],"CPC":[78],"only":[79],"looks":[80],"at":[81,104,239,245],"audio":[83],"signal’s":[84],"frame-level":[85,116,156],"structure.":[86],"We":[87,179,209,268],"overcome":[88],"this":[89],"limitation":[90],"with":[91],"segmental":[93],"(SCPC)":[97],"framework":[98],"to":[99,137,144,154,235,262,280],"model":[100,166],"signal":[102],"structure":[103],"higher":[106],"level,":[107],"e.g.,":[108],"phone":[109,169,212,300],"level.":[110],"A":[111,126],"convolutional":[112],"neural":[113],"network":[114],"learns":[115],"representation":[117],"raw":[120],"waveform":[121],"noise-contrastive":[123],"estimation":[124],"(NCE).":[125],"differentiable":[127,149],"boundary":[128,150,187,198,216],"detector":[129,151,188],"finds":[130],"variable-length":[131],"segments,":[132],"then":[135],"used":[136],"optimize":[138],"segment":[140,146,241],"encoder":[141],"NCE":[143],"learn":[145],"representations.":[147],"The":[148],"allows":[152],"us":[153],"train":[155],"segment-level":[158],"encoders":[159],"jointly.":[160],"Experiments":[161],"show":[162],"our":[164,191],"single":[165],"outperforms":[167],"existing":[168],"word":[171],"on":[174,186,286,297],"TIMIT":[175],"Buckeye":[177],"datasets.":[178],"analyze":[180],"impact":[182],"threshold":[185,199],"performance,":[189,218],"results":[192],"suggest":[193],"automatically":[195],"learning":[196],"be":[201],"effective":[203],"manually":[205],"tuning":[206],"threshold.":[208],"discover":[210],"class":[213],"impacts":[214],"detection":[217],"boundaries":[221],"between":[222],"successive":[223],"vowels":[224],"or":[225],"semivowels":[226],"most":[229],"difficult.":[230],"Finally,":[231],"use":[233],"SCPC":[234],"extract":[236],"features":[238,293],"level":[242,250],"rather":[243],"than":[244],"uniformly":[247],"spaced":[248],"(e.g.,":[251],"10":[252],"ms)":[253],"produce":[255],"variable":[256],"rate":[257,274],"representations":[258],"change":[260],"according":[261],"contents":[264],"utterance.":[267],"lower":[270],"feature":[272],"extraction":[273],"typical":[277],"100":[278],"Hz":[279,285],"low":[282],"14.5":[284],"average":[287],"while":[288],"still":[289],"outperforming":[290],"hand-crafted":[292],"MFCC":[296],"linear":[299],"classification":[301],"task.":[302]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-25T15:57:00.446498","created_date":"2025-10-10T00:00:00"}