{"id":"https://openalex.org/W2404799143","doi":"https://doi.org/10.21437/interspeech.2015-640","title":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","display_name":"A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2404799143","doi":"https://doi.org/10.21437/interspeech.2015-640","mag":"2404799143"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-640","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-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/A5031635550","display_name":"Roland Thiolli\u00e8re","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roland Thiolli\u00e8re","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069239428","display_name":"Ewan Dunbar","orcid":"https://orcid.org/0000-0001-9603-953X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ewan Dunbar","raw_affiliation_strings":["University of Maryland - College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055225582","display_name":"Maarten Versteegh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maarten Versteegh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007620149","display_name":"Emmanuel Dupoux","orcid":"https://orcid.org/0000-0002-7814-2952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emmanuel Dupoux","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.6907,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98903994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7491151690483093},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7294301986694336},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.7218649983406067},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6820246577262878},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5393427014350891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5272007584571838},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4170811176300049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3856087327003479},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.337772011756897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7491151690483093},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7294301986694336},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.7218649983406067},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6820246577262878},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5393427014350891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5272007584571838},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4170811176300049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3856087327003479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.337772011756897},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-640","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W21006490","https://openalex.org/W148837159","https://openalex.org/W904206136","https://openalex.org/W1545920196","https://openalex.org/W1606347560","https://openalex.org/W1972159947","https://openalex.org/W1985371235","https://openalex.org/W1993755070","https://openalex.org/W1997460147","https://openalex.org/W2048741136","https://openalex.org/W2052697931","https://openalex.org/W2054948443","https://openalex.org/W2057007397","https://openalex.org/W2079623482","https://openalex.org/W2114347655","https://openalex.org/W2127589108","https://openalex.org/W2138621090","https://openalex.org/W2164770604","https://openalex.org/W2171590421","https://openalex.org/W2251545788","https://openalex.org/W2608958052","https://openalex.org/W2619993508","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2350336482","https://openalex.org/W2154472250","https://openalex.org/W2229352698","https://openalex.org/W2130799169","https://openalex.org/W2340348677"],"abstract_inverted_index":{"We":[0,75],"report":[1],"on":[2],"an":[3],"architecture":[4],"for":[5],"the":[6,44,48,54,63,68,81,97,102,112],"unsupervised":[7],"discovery":[8,26],"of":[9,17,60,62,72,84,101],"talker-invariant":[10],"subword":[11,115],"embeddings.":[12],"It":[13],"is":[14,50],"made":[15],"out":[16],"two":[18],"components:":[19],"a":[20,30],"dynamic-time":[21],"warping":[22],"based":[23],"spoken":[24],"term":[25],"(STD)":[27],"system":[28,38],"and":[29,66,99],"Siamese":[31],"deep":[32],"neural":[33],"network":[34],"(DNN).":[35],"The":[36,107],"STD":[37],"clusters":[39],"word-sized":[40],"repeated":[41],"fragments":[42],"in":[43,114],"acoustic":[45],"streams":[46],"while":[47],"DNN":[49],"trained":[51],"to":[52],"minimize":[53],"distance":[55,69],"between":[56,70],"time":[57],"aligned":[58],"frames":[59],"tokens":[61,71],"same":[64],"cluster,":[65],"maximize":[67],"different":[73],"clusters.":[74],"use":[76,96],"additional":[77],"side":[78],"information":[79],"regarding":[80],"average":[82],"duration":[83],"phonemic":[85],"units,":[86],"as":[87,89],"well":[88],"talker":[90],"identity":[91],"tags.":[92],"For":[93],"evaluation":[94],"we":[95],"datasets":[98],"metrics":[100],"Zero":[103],"Resource":[104],"Speech":[105],"Challenge.":[106],"model":[108],"shows":[109],"improvement":[110],"over":[111],"baseline":[113],"unit":[116],"modeling.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}