{"id":"https://openalex.org/W3043897409","doi":"https://doi.org/10.21437/interspeech.2020-2398","title":"Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation","display_name":"Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3043897409","doi":"https://doi.org/10.21437/interspeech.2020-2398","mag":"3043897409"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2398","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2007.13465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000406733","display_name":"Felix Kreuk","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Felix Kreuk","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Bar-Ilan University, Ramat Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":["Meta (Israel), Tel Aviv, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta (Israel), Tel Aviv, Israel","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3700","last_page":"3704"},"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9983000159263611,"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/timit","display_name":"TIMIT","score":0.8112667798995972},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7948383688926697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6448659300804138},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5677531361579895},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5412203669548035},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4852037727832794},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.47200724482536316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45321956276893616},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4319761097431183},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41195109486579895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3602169156074524},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.217400461435318}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8112667798995972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948383688926697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448659300804138},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5677531361579895},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5412203669548035},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4852037727832794},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.47200724482536316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45321956276893616},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4319761097431183},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41195109486579895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3602169156074524},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.217400461435318},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2398","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2398","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.13465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.13465","pdf_url":"https://arxiv.org/pdf/2007.13465","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3043897409","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.13465.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2007.13465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.13465","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.13465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.13465","pdf_url":"https://arxiv.org/pdf/2007.13465","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043897409.pdf","grobid_xml":"https://content.openalex.org/works/W3043897409.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W333962176","https://openalex.org/W1494198834","https://openalex.org/W1558402681","https://openalex.org/W1761091820","https://openalex.org/W2017814685","https://openalex.org/W2069732686","https://openalex.org/W2074394031","https://openalex.org/W2077828209","https://openalex.org/W2083904075","https://openalex.org/W2096270777","https://openalex.org/W2116656681","https://openalex.org/W2124343046","https://openalex.org/W2151244813","https://openalex.org/W2152790380","https://openalex.org/W2171752983","https://openalex.org/W2223030742","https://openalex.org/W2404952642","https://openalex.org/W2542955097","https://openalex.org/W2601836666","https://openalex.org/W2620638943","https://openalex.org/W2747874407","https://openalex.org/W2842511635","https://openalex.org/W2963137467","https://openalex.org/W2963341956","https://openalex.org/W2964079874","https://openalex.org/W2965373594","https://openalex.org/W2973049979","https://openalex.org/W3005680577","https://openalex.org/W3006094508","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W3096656254","https://openalex.org/W2906122999","https://openalex.org/W2117041980","https://openalex.org/W3169072315","https://openalex.org/W2107240889","https://openalex.org/W2499126254","https://openalex.org/W2786902352","https://openalex.org/W2296452459","https://openalex.org/W23007503","https://openalex.org/W1942713348","https://openalex.org/W2757717328","https://openalex.org/W2100768664","https://openalex.org/W2531863702","https://openalex.org/W1985084205","https://openalex.org/W3015265920","https://openalex.org/W2620025177","https://openalex.org/W3013060758","https://openalex.org/W1796128977","https://openalex.org/W3160200310","https://openalex.org/W2594951208"],"abstract_inverted_index":{"We":[0,87,134],"propose":[1],"a":[2,18,47,70],"self-supervised":[3],"representation":[4],"learning":[5],"model":[6,16,55,66,138,165],"for":[7,164],"the":[8,26,37,40,54,59,64,79,89,108,124,131,136,148],"task":[9],"of":[10,81],"unsupervised":[11,72,94],"phoneme":[12],"boundary":[13],"detection.":[14],"The":[15],"is":[17,30,51,67,162],"convolutional":[19],"neural":[20],"network":[21],"that":[22,104,143,157],"operates":[23],"directly":[24],"on":[25,115,139],"raw":[27],"waveform.":[28],"It":[29],"optimized":[31],"to":[32,57,92],"identify":[33],"spectral":[34],"changes":[35],"in":[36,69,78],"signal":[38],"using":[39,96],"Noise-Contrastive":[41],"Estimation":[42],"principle.":[43],"At":[44],"test":[45],"time,":[46],"peak":[48],"detection":[49],"algorithm":[50],"applied":[52],"over":[53],"outputs":[56],"produce":[58],"final":[60],"boundaries.":[61],"As":[62],"such,":[63],"proposed":[65,90],"trained":[68],"fully":[71],"manner":[73],"with":[74,122,127],"no":[75],"manual":[76],"annotations":[77],"form":[80],"target":[82],"boundaries":[83],"nor":[84],"phonetic":[85],"transcriptions.":[86],"compare":[88],"approach":[91,106],"several":[93],"baselines":[95],"both":[97,116],"TIMIT":[98],"and":[99,111,141,153,155],"Buckeye":[100],"corpora.":[101],"Results":[102],"suggest":[103],"our":[105],"surpasses":[107],"baseline":[109],"models":[110],"reaches":[112],"state-of-the-art":[113],"performance":[114],"data":[117,161],"sets.":[118],"Furthermore,":[119],"we":[120],"experimented":[121],"expanding":[123],"training":[125,149],"set":[126],"additional":[128,159],"examples":[129],"from":[130],"Librispeech":[132],"corpus.":[133],"evaluated":[135],"resulting":[137],"distributions":[140],"languages":[142],"were":[144],"not":[145],"seen":[146],"during":[147],"phase":[150],"(English,":[151],"Hebrew":[152],"German)":[154],"showed":[156],"utilizing":[158],"untranscribed":[160],"beneficial":[163],"performance.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}