{"id":"https://openalex.org/W3033038061","doi":"https://doi.org/10.21437/interspeech.2020-3084","title":"A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning","display_name":"A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3033038061","doi":"https://doi.org/10.21437/interspeech.2020-3084","mag":"3033038061"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3084","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":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.02547","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035187454","display_name":"Sameer Khurana","orcid":"https://orcid.org/0000-0002-3182-1085"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210102556","display_name":"K Lab (United States)","ror":"https://ror.org/010zs2155","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sameer Khurana","raw_affiliation_strings":["MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab (United States)","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210102556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210102556","display_name":"K Lab (United States)","ror":"https://ror.org/010zs2155","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab (United States)","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210102556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000408865","display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I219388962","display_name":"University of Wroc\u0142aw","ror":"https://ror.org/00yae6e25","country_code":"PL","type":"education","lineage":["https://openalex.org/I219388962"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["UWr - University of Wroc\u0142aw [Poland] (Pl. Uniwersytecki 1 \r\n50-137 Wroc\u0142aw - Poland)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UWr - University of Wroc\u0142aw [Poland] (Pl. Uniwersytecki 1 \r\n50-137 Wroc\u0142aw - Poland)","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011669714","display_name":"Adrian \u0141a\u0144cucki","orcid":null},"institutions":[{"id":"https://openalex.org/I219388962","display_name":"University of Wroc\u0142aw","ror":"https://ror.org/00yae6e25","country_code":"PL","type":"education","lineage":["https://openalex.org/I219388962"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Adrian Lancucki","raw_affiliation_strings":["UWr - University of Wroc\u0142aw [Poland] (Pl. Uniwersytecki 1 \r\n50-137 Wroc\u0142aw - Poland)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UWr - University of Wroc\u0142aw [Poland] (Pl. Uniwersytecki 1 \r\n50-137 Wroc\u0142aw - Poland)","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["DYNI - DYNamiques de l\u2019Information (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DYNI - DYNamiques de l\u2019Information (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210102556","display_name":"K Lab (United States)","ror":"https://ror.org/010zs2155","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab (United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab (United States)","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210102556"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5035187454"],"corresponding_institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210102556"],"apc_list":null,"apc_paid":null,"fwci":3.1278,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93157513,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3790","last_page":"3794"},"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":0.9975000023841858,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.7104609608650208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6990365982055664},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5709977149963379},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5676304697990417},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5414372682571411},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5310222506523132},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5237246155738831},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5140017867088318},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4949747920036316},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48291346430778503},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48195573687553406},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4449538290500641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7104609608650208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6990365982055664},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5709977149963379},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5676304697990417},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5414372682571411},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5310222506523132},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5237246155738831},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5140017867088318},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4949747920036316},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48291346430778503},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48195573687553406},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4449538290500641},{"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/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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-3084","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3084","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:2006.02547","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02547","pdf_url":"https://arxiv.org/pdf/2006.02547","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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02912029v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02912029","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2020, Oct 2020, Shanghai, China","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2006.02547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.02547","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:2006.02547","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.02547","pdf_url":"https://arxiv.org/pdf/2006.02547","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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2068247585","https://openalex.org/W2100768664","https://openalex.org/W2126377586","https://openalex.org/W2127141656","https://openalex.org/W2134952451","https://openalex.org/W2153185114","https://openalex.org/W2210838531","https://openalex.org/W2347098582","https://openalex.org/W2483390977","https://openalex.org/W2556930864","https://openalex.org/W2750248772","https://openalex.org/W2787698019","https://openalex.org/W2793111190","https://openalex.org/W2807947437","https://openalex.org/W2808697642","https://openalex.org/W2926063217","https://openalex.org/W2926827382","https://openalex.org/W2935542736","https://openalex.org/W2937090315","https://openalex.org/W2941814890","https://openalex.org/W2944828972","https://openalex.org/W2948211236","https://openalex.org/W2949382160","https://openalex.org/W2949517790","https://openalex.org/W2951004968","https://openalex.org/W2953331651","https://openalex.org/W2962695963","https://openalex.org/W2962990490","https://openalex.org/W2963300588","https://openalex.org/W2963618559","https://openalex.org/W2964232608","https://openalex.org/W2970014727","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W2995085126","https://openalex.org/W2995680346","https://openalex.org/W3101749733","https://openalex.org/W3125709657"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W2001275470","https://openalex.org/W2073996508","https://openalex.org/W1591475660","https://openalex.org/W3145575561","https://openalex.org/W2164162849"],"abstract_inverted_index":{"Probabilistic":[0],"Latent":[1],"Variable":[2],"Models":[3],"(LVMs)":[4],"provide":[5],"an":[6,20,104,182],"alternative":[7],"to":[8,45],"self-supervised":[9,127,149],"learning":[10,15,57,173],"approaches":[11],"for":[12,54,107],"linguistic":[13],"representation":[14,56],"from":[16,32],"speech.":[17],"LVMs":[18,37],"admit":[19],"intuitive":[21],"probabilistic":[22],"interpretation":[23],"where":[24],"the":[25,29,33,46,138,157,163],"latent":[26],"structure":[27],"shapes":[28],"information":[30],"extracted":[31],"signal.":[34],"Even":[35],"though":[36],"have":[38],"recently":[39],"seen":[40],"a":[41,71,114],"renewed":[42],"interest":[43],"due":[44],"introduction":[47],"of":[48,162],"Variational":[49],"Autoencoders":[50],"(VAEs),":[51],"their":[52],"use":[53],"speech":[55,117],"remains":[58],"largely":[59],"unexplored.":[60],"In":[61],"this":[62],"work,":[63],"we":[64,144,167],"propose":[65],"Convolutional":[66],"Deep":[67],"Markov":[68],"Model":[69],"(ConvDMM),":[70],"Gaussian":[72],"state-space":[73],"model":[74,88],"with":[75,160,186],"non-linear":[76],"emission":[77],"and":[78,135,153],"transition":[79],"functions":[80],"modelled":[81],"by":[82],"deep":[83,97],"neural":[84,99],"networks.":[85],"This":[86],"unsupervised":[87],"is":[89,101],"trained":[90,112],"using":[91],"black":[92],"box":[93],"variational":[94,109],"inference.":[95],"A":[96],"convolutional":[98],"network":[100,106],"used":[102],"as":[103],"inference":[105],"structured":[108],"approximation.":[110],"When":[111],"on":[113,131,137,156],"large":[115],"scale":[116],"dataset":[118],"(LibriSpeech),":[119],"ConvDMM":[120,147,170],"produces":[121],"features":[122,171,180],"that":[123,146,169],"significantly":[124],"outperform":[125],"multiple":[126],"feature":[128],"extracting":[129],"methods":[130,150,164],"linear":[132],"phone":[133,175],"classification":[134],"recognition":[136],"Wall":[139],"Street":[140],"Journal":[141],"dataset.":[142],"Furthermore,":[143],"found":[145],"complements":[148],"like":[151],"Wav2Vec":[152],"PASE,":[154],"improving":[155],"results":[158],"achieved":[159],"any":[161,178],"alone.":[165],"Lastly,":[166],"find":[168],"enable":[172],"better":[174],"recognizers":[176],"than":[177],"other":[179],"in":[181],"extreme":[183],"low-resource":[184],"regime":[185],"few":[187],"labeled":[188],"training":[189],"examples.":[190]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2022-07-25T00:00:00"}