{"id":"https://openalex.org/W2798803900","doi":"https://doi.org/10.21437/interspeech.2018-2384","title":"Sampling Strategies in Siamese Networks for Unsupervised Speech Representation Learning","display_name":"Sampling Strategies in Siamese Networks for Unsupervised Speech Representation Learning","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2798803900","doi":"https://doi.org/10.21437/interspeech.2018-2384","mag":"2798803900"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2384","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1804.11297","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040825352","display_name":"Rachid Riad","orcid":"https://orcid.org/0000-0002-7753-1219"},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Rachid Riad","raw_affiliation_strings":["\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France"],"affiliations":[{"raw_affiliation_string":"\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France","institution_ids":["https://openalex.org/I90669466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046767053","display_name":"Corentin Dancette","orcid":null},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Corentin Dancette","raw_affiliation_strings":["\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France"],"affiliations":[{"raw_affiliation_string":"\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France","institution_ids":["https://openalex.org/I90669466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085852900","display_name":"Julien Karadayi","orcid":null},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Julien Karadayi","raw_affiliation_strings":["\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France"],"affiliations":[{"raw_affiliation_string":"\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France","institution_ids":["https://openalex.org/I90669466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047639590","display_name":"Neil Zeghidour","orcid":"https://orcid.org/0000-0001-6896-3987"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Neil Zeghidour","raw_affiliation_strings":["Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris-Saclay, Gif-sur-Yvette, France","institution_ids":["https://openalex.org/I277688954"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Schatz","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Schatz","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[{"id":"https://openalex.org/I90669466","display_name":"\u00c9cole des hautes \u00e9tudes en sciences sociales","ror":"https://ror.org/02d9dg697","country_code":"FR","type":"facility","lineage":["https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":["\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France"],"affiliations":[{"raw_affiliation_string":"\u00c9cole des hautes \u00e9tudes en sciences sociales, Villejuif, France","institution_ids":["https://openalex.org/I90669466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5040825352"],"corresponding_institution_ids":["https://openalex.org/I90669466"],"apc_list":null,"apc_paid":null,"fwci":0.3385,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6726661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2658","last_page":"2662"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9980000257492065,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9944000244140625,"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":0.6591243147850037},{"id":"https://openalex.org/keywords/zipfs-law","display_name":"Zipf's law","score":0.6444298624992371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5794294476509094},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5646257996559143},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5433770418167114},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.532080888748169},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5080265998840332},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.48892465233802795},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4070640802383423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4055611789226532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3204723000526428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2141129970550537},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16720816493034363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591243147850037},{"id":"https://openalex.org/C125932096","wikidata":"https://www.wikidata.org/wiki/Q205472","display_name":"Zipf's law","level":2,"score":0.6444298624992371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5794294476509094},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5646257996559143},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5433770418167114},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.532080888748169},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5080265998840332},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.48892465233802795},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4070640802383423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4055611789226532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3204723000526428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2141129970550537},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16720816493034363},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-2384","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1804.11297","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.11297","pdf_url":"https://arxiv.org/pdf/1804.11297","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":"pmh:oai:HAL:hal-01888725v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01888725","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2018, Sep 2018, Hyderabad, India","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1804.11297","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1804.11297","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1804.11297","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1804.11297","pdf_url":"https://arxiv.org/pdf/1804.11297","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798803900.pdf","grobid_xml":"https://content.openalex.org/works/W2798803900.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W1522301498","https://openalex.org/W1545920196","https://openalex.org/W1615991656","https://openalex.org/W1796128977","https://openalex.org/W2052697931","https://openalex.org/W2145410271","https://openalex.org/W2160815625","https://openalex.org/W2251025892","https://openalex.org/W2316904474","https://openalex.org/W2345811097","https://openalex.org/W2347145335","https://openalex.org/W2395899413","https://openalex.org/W2399576818","https://openalex.org/W2400549570","https://openalex.org/W2404799143","https://openalex.org/W2406349064","https://openalex.org/W2786608204","https://openalex.org/W2949117887"],"related_works":["https://openalex.org/W2962850179","https://openalex.org/W3098361150","https://openalex.org/W2768029001","https://openalex.org/W2556021077","https://openalex.org/W2979390460","https://openalex.org/W2904632276","https://openalex.org/W2808428547","https://openalex.org/W2964548769","https://openalex.org/W2950577311","https://openalex.org/W2132339004","https://openalex.org/W2903988268","https://openalex.org/W2252025371","https://openalex.org/W2805273321","https://openalex.org/W3137093496","https://openalex.org/W2891378076","https://openalex.org/W2891566965","https://openalex.org/W2805334656","https://openalex.org/W3028222090","https://openalex.org/W2251183320","https://openalex.org/W61571138"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"investigated":[3],"siamese":[4,29,145],"network":[5],"architectures":[6],"for":[7],"learning":[8,83,143],"invariant":[9],"speech":[10],"representations":[11],"using":[12,130,144],"same-different":[13,113],"side":[14],"information":[15],"at":[16],"the":[17,31,53,58,69,72,101,105,110],"word":[18,79],"level.":[19],"Here":[20],"we":[21,76],"investigate":[22],"systematically":[23],"an":[24,131,136],"often":[25],"ignored":[26],"component":[27],"of":[28,36,55,60,65,71,88,92,112,127],"networks:":[30],"sampling":[32,46],"procedure":[33],"(how":[34],"pairs":[35,64,111,126],"same":[37,61,102],"vs.":[38],"different":[39,63],"tokens":[40],"are":[41,115],"selected).":[42],"We":[43,121],"show":[44,77,135],"that":[45,78],"strategies":[47],"taking":[48],"into":[49],"account":[50],"Zipf's":[51],"Law,":[52],"distribution":[54],"speakers":[56],"and":[57,62,134],"proportions":[59],"words":[66,114,128],"significantly":[67],"impact":[68],"performance":[70],"network.":[73],"In":[74],"particular,":[75],"frequency":[80],"compression":[81],"improves":[82],"across":[84],"a":[85],"large":[86],"range":[87],"variations":[89],"in":[90,140],"number":[91],"training":[93],"pairs.":[94],"This":[95],"effect":[96],"does":[97],"not":[98],"apply":[99,122],"to":[100,104,125],"extent":[103],"fully":[106],"unsupervised":[107,132,141],"setting,":[108],"where":[109],"obtained":[116],"by":[117],"spoken":[118],"term":[119],"discovery.":[120],"these":[123],"results":[124],"discovered":[129],"algorithm":[133],"improvement":[137],"on":[138],"state-of-the-art":[139],"representation":[142],"networks.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2019-07-30T00:00:00"}