{"id":"https://openalex.org/W3169072315","doi":"https://doi.org/10.21437/interspeech.2021-1874","title":"Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation","display_name":"Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3169072315","doi":"https://doi.org/10.21437/interspeech.2021-1874","mag":"3169072315"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1874","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.02170","any_repository_has_fulltext":true},"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":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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":"Jes\u00fas Villalba","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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 \u017belasko","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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-Vel\u00e1zquez","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","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":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9987000226974487,"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":0.7688623666763306},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6115188002586365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5973042249679565},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5780764818191528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5457507967948914},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48629555106163025},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.45551908016204834},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.433095246553421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688623666763306},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6115188002586365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5973042249679565},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5780764818191528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457507967948914},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48629555106163025},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.45551908016204834},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.433095246553421},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1874","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.02170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.02170","pdf_url":"https://arxiv.org/pdf/2106.02170","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"},{"id":"doi:10.48550/arxiv.2106.02170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.02170","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3169072315","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.02170","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.02170","pdf_url":"https://arxiv.org/pdf/2106.02170","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":[{"id":"https://metadata.un.org/sdg/4","score":0.5400000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3169072315.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W2020607164","https://openalex.org/W2057007397","https://openalex.org/W2078769636","https://openalex.org/W2100768664","https://openalex.org/W2117126688","https://openalex.org/W2126377586","https://openalex.org/W2145410271","https://openalex.org/W2152790380","https://openalex.org/W2170659185","https://openalex.org/W2242818861","https://openalex.org/W2468716020","https://openalex.org/W2478415332","https://openalex.org/W2601836666","https://openalex.org/W2747192917","https://openalex.org/W2842511635","https://openalex.org/W2890718354","https://openalex.org/W2940544976","https://openalex.org/W2963137467","https://openalex.org/W2963799213","https://openalex.org/W2964169922","https://openalex.org/W2972794572","https://openalex.org/W2973049979","https://openalex.org/W2996383576","https://openalex.org/W3027324582","https://openalex.org/W3036601975","https://openalex.org/W3096656254","https://openalex.org/W3099782249","https://openalex.org/W3112613336","https://openalex.org/W3125709657","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2906122999","https://openalex.org/W3096656254","https://openalex.org/W3013060758","https://openalex.org/W2033413759","https://openalex.org/W65317819","https://openalex.org/W1942713348","https://openalex.org/W2899069432","https://openalex.org/W1559312645","https://openalex.org/W2620025177","https://openalex.org/W2785415724","https://openalex.org/W2478415332","https://openalex.org/W2486205537","https://openalex.org/W2747943889","https://openalex.org/W2099098972","https://openalex.org/W2889245478","https://openalex.org/W1796128977","https://openalex.org/W175164482","https://openalex.org/W1986410788","https://openalex.org/W2115412984","https://openalex.org/W2057817554"],"abstract_inverted_index":{"Automatic":[0],"detection":[1],"of":[2,9,164],"phoneme":[3,73,129,150],"or":[4],"word-like":[5],"units":[6],"is":[7,33,169],"one":[8],"the":[10,30,43,63,72,86,162,170,175,179],"core":[11],"objectives":[12],"in":[13,178],"zero-resource":[14],"speech":[15],"processing.":[16],"Recent":[17],"attempts":[18],"employ":[19],"self-supervised":[20],"training":[21],"methods,":[22],"such":[23],"as":[24,135],"contrastive":[25,55],"predictive":[26,56],"coding":[27,57],"(CPC),":[28],"where":[29],"next":[31],"frame":[32],"predicted":[34],"given":[35],"past":[36],"context.":[37],"However,":[38],"CPC":[39],"only":[40],"looks":[41],"at":[42,66,71],"audio":[44],"signal's":[45],"frame-level":[46,83,123],"structure.":[47],"We":[48,138,160],"overcome":[49],"this":[50,76],"limitation":[51],"with":[52],"a":[53,67,78,106],"segmental":[54,176],"(SCPC)":[58],"framework":[59],"that":[60,144],"can":[61],"model":[62,147],"signal":[64],"structure":[65],"higher":[68],"level":[69],"e.g.":[70],"level.":[74],"In":[75],"framework,":[77],"convolutional":[79],"neural":[80],"network":[81],"learns":[82],"representation":[84],"from":[85],"raw":[87],"waveform":[88],"via":[89,109],"noise-contrastive":[90],"estimation":[91],"(NCE).":[92],"A":[93],"differentiable":[94,116],"boundary":[95,117,165],"detector":[96,118],"finds":[97],"variable-length":[98],"segments,":[99],"which":[100],"are":[101,133],"then":[102],"used":[103],"to":[104,111,121,173],"optimize":[105],"segment":[107,113],"encoder":[108],"NCE":[110],"learn":[112],"representations.":[114],"The":[115],"allows":[119],"us":[120],"train":[122],"and":[124,130,141,151,157,167],"segment-level":[125],"encoders":[126],"jointly.":[127],"Typically,":[128],"word":[131,152],"segmentation":[132,153],"treated":[134],"separate":[136],"tasks.":[137],"unify":[139],"them":[140],"experimentally":[142],"show":[143],"our":[145],"single":[146],"outperforms":[148],"existing":[149],"methods":[154],"on":[155],"TIMIT":[156],"Buckeye":[158],"datasets.":[159],"analyze":[161],"impact":[163],"threshold":[166],"when":[168],"right":[171],"time":[172],"include":[174],"loss":[177],"learning":[180],"process.":[181]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}