{"id":"https://openalex.org/W2927191280","doi":"https://doi.org/10.21437/interspeech.2019-2224","title":"Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery","display_name":"Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2927191280","doi":"https://doi.org/10.21437/interspeech.2019-2224","mag":"2927191280"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2224","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03876","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104831405","display_name":"Lucas Ondel","orcid":"https://orcid.org/0000-0003-4512-0471"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":["Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hari Krishna Vydana","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Hari Krishna Vydana","raw_affiliation_strings":["Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":["Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":["Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0245,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89870209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"261","last_page":"265"},"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":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8932876586914062},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8024060726165771},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7762966752052307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7602745294570923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6255587339401245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5527726411819458},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5271967053413391},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5188135504722595},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45771780610084534},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.45062685012817383},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4448113441467285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41949188709259033},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41324612498283386},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.3511750400066376},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.16592922806739807}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8932876586914062},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8024060726165771},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7762966752052307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602745294570923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6255587339401245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5527726411819458},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5271967053413391},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5188135504722595},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45771780610084534},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.45062685012817383},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4448113441467285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41949188709259033},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41324612498283386},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3511750400066376},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.16592922806739807},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2224","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2224","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03876","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03876","pdf_url":"https://arxiv.org/pdf/1904.03876","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03876","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03876","pdf_url":"https://arxiv.org/pdf/1904.03876","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":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1319050382","display_name":null,"funder_award_id":"19-26934X","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"},{"id":"https://openalex.org/G1503666391","display_name":null,"funder_award_id":"FA8650-17-C-9118","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G656068760","display_name":null,"funder_award_id":"FA8650-17-C-9118","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G853342598","display_name":null,"funder_award_id":"LQ1602","funder_id":"https://openalex.org/F4320321006","funder_display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312530","display_name":"Office of the Director of National Intelligence","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2927191280.pdf","grobid_xml":"https://content.openalex.org/works/W2927191280.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W1524333225","https://openalex.org/W1959608418","https://openalex.org/W2055408826","https://openalex.org/W2077804127","https://openalex.org/W2084534958","https://openalex.org/W2100768664","https://openalex.org/W2125838338","https://openalex.org/W2347098582","https://openalex.org/W2468716020","https://openalex.org/W2641832364","https://openalex.org/W2730658205","https://openalex.org/W2750248772","https://openalex.org/W2888911345","https://openalex.org/W2962693497","https://openalex.org/W2964121744","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2083296885","https://openalex.org/W2121652828","https://openalex.org/W2126322296"],"abstract_inverted_index":{"This":[0],"work":[1],"tackles":[2],"the":[3,31,36,39,49,59,67,77,111,140],"problem":[4],"of":[5,9,20,41],"learning":[6],"a":[7,18,73,93],"set":[8,19],"language":[10],"specific":[11],"acoustic\\nunits":[12],"from":[13,44,103],"unlabeled":[14],"speech":[15],"recordings":[16,22],"given":[17],"labeled":[21],"from\\nother":[23],"languages.":[24],"Our":[25],"approach":[26,127],"may":[27],"be":[28],"described":[29],"by":[30],"following":[32],"two":[33],"steps\\nprocedure:":[34],"first":[35],"model":[37,50,74],"learns":[38],"notion":[40],"acoustic":[42,57,89,133],"units":[43],"the\\nlabelled":[45],"data":[46],"and":[47,108,110,136],"then":[48],"uses":[51],"its":[52],"knowledge":[53],"to":[54,76],"find":[55],"new":[56],"units\\non":[58],"target":[60],"language.":[61],"We":[62],"implement":[63],"this":[64],"process":[65],"with":[66,139],"Bayesian":[68],"Subspace\\nHidden":[69],"Markov":[70],"Model":[71],"(SHMM),":[72],"akin":[75],"Subspace":[78],"Gaussian":[79],"Mixture":[80],"Model\\n(SGMM)":[81],"where":[82],"each":[83],"low":[84],"dimensional":[85],"embedding":[86],"represents":[87],"an":[88],"unit":[90],"rather\\nthan":[91],"just":[92],"HMM's":[94],"state.":[95],"The":[96],"subspace":[97],"is":[98],"trained":[99],"on":[100],"3":[101],"languages":[102],"the\\nGlobalPhone":[104],"corpus":[105],"(German,":[106],"Polish":[107],"Spanish)":[109],"AUs":[112],"are":[113],"discovered":[114],"on\\nthe":[115],"TIMIT":[116],"corpus.":[117],"Results,":[118],"measured":[119],"in":[120],"equivalent":[121],"Phone":[122],"Error":[123],"Rate,":[124],"show":[125],"that\\nthis":[126],"significantly":[128],"outperforms":[129],"previous":[130],"HMM":[131],"based":[132],"units\\ndiscovery":[134],"systems":[135],"compares":[137],"favorably":[138],"Variational":[141],"Auto":[142],"Encoder-HMM.\\n":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}