{"id":"https://openalex.org/W2888911345","doi":"https://doi.org/10.21437/interspeech.2018-2148","title":"Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery","display_name":"Full Bayesian Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888911345","doi":"https://doi.org/10.21437/interspeech.2018-2148","mag":"2888911345"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2148","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":["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/A5034662562","display_name":"Thomas Glarner","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Thomas Glarner","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060910737","display_name":"Patrick Hanebrink","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Hanebrink","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055580486","display_name":"Janek Ebbers","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Janek Ebbers","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034662562"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9726,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92421932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2688","last_page":"2692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.989300012588501,"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":0.7398044466972351},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7243430614471436},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6227333545684814},{"id":"https://openalex.org/keywords/hidden-semi-markov-model","display_name":"Hidden semi-Markov model","score":0.5789199471473694},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5596470832824707},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4407525062561035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4344308376312256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39898693561553955},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.38202977180480957},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.38115254044532776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.370431125164032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3305661678314209},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29685288667678833},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.29163849353790283},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2673701047897339},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2248142659664154}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7398044466972351},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7243430614471436},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6227333545684814},{"id":"https://openalex.org/C64939953","wikidata":"https://www.wikidata.org/wiki/Q3859882","display_name":"Hidden semi-Markov model","level":5,"score":0.5789199471473694},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5596470832824707},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4407525062561035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4344308376312256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39898693561553955},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.38202977180480957},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.38115254044532776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.370431125164032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3305661678314209},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29685288667678833},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.29163849353790283},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2673701047897339},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2248142659664154},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-2148","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2148","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1833498382","https://openalex.org/W2127498532","https://openalex.org/W2142384583","https://openalex.org/W2347098582","https://openalex.org/W2468716020","https://openalex.org/W2750248772","https://openalex.org/W2753738274","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2316449557","https://openalex.org/W2379938888","https://openalex.org/W4246505579","https://openalex.org/W2134386692","https://openalex.org/W2103649304","https://openalex.org/W3044198794","https://openalex.org/W2116722627","https://openalex.org/W2176285001","https://openalex.org/W2537260108"],"abstract_inverted_index":{"The":[0,29],"invention":[1],"of":[2,9,16,24,42,88,131,160],"the":[3,7,22,54,68,77,81,86,95,103,117,129,132,150,186,190],"Variational":[4,35,108],"Autoencoder":[5,36,109],"enables":[6],"application":[8],"Neural":[10],"Networks":[11],"to":[12,154],"a":[13,39,43,50,59,120,124,157,169],"wide":[14],"range":[15],"tasks":[17],"in":[18,119],"unsupervised":[19],"learning,":[20],"including":[21],"field":[23],"Acoustic":[25],"Unit":[26],"Discovery":[27],"(AUD).":[28],"recently":[30],"proposed":[31],"Hidden":[32,60,105],"Markov":[33,61,106],"Model":[34,107],"(HMMVAE)":[37],"allows":[38],"joint":[40],"training":[41],"neural":[44],"network":[45],"based":[46,74],"feature":[47],"extractor":[48],"and":[49,91,135,146],"structured":[51],"prior":[52],"for":[53,98,128],"latent":[55],"space":[56],"given":[57],"by":[58,115,168,178],"Model.":[62],"It":[63],"has":[64],"been":[65],"shown":[66],"that":[67,149],"HMMVAE":[69,82,118],"significantly":[70],"outperforms":[71],"pure":[72],"GMM-HMM":[73,96,170],"systems":[75],"on":[76,94,144],"AUD":[78,187],"task.":[79],"However,":[80],"cannot":[83],"autonomously":[84,155],"infer":[85,156],"number":[87,159],"acoustic":[89,133,161],"units":[90],"thus":[92],"relies":[93],"system":[97],"initialization.":[99],"This":[100],"paper":[101],"introduces":[102],"Bayesian":[104,121],"(BHMMVAE)":[110],"which":[111],"solves":[112],"these":[113],"issues":[114],"embedding":[116],"framework":[122],"with":[123],"Dirichlet":[125],"Process":[126],"Prior":[127],"distribution":[130],"units,":[134,162],"diagonal":[136],"or":[137],"full-covariance":[138],"Gaussians":[139],"as":[140],"emission":[141],"distributions.":[142],"Experiments":[143],"TIMIT":[145],"Xitsonga":[147],"show":[148],"BHMMVAE":[151],"is":[152],"able":[153],"reasonable":[158],"can":[163],"be":[164],"initialized":[165],"without":[166],"supervision":[167],"system,":[171],"achieves":[172],"computationally":[173],"efficient":[174],"stochastic":[175],"variational":[176],"inference":[177],"using":[179],"natural":[180],"gradient":[181],"descent,":[182],"and,":[183],"additionally,":[184],"improves":[185],"performance":[188],"over":[189],"HMMVAE.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}