{"id":"https://openalex.org/W2063385039","doi":"https://doi.org/10.1109/waspaa.2013.6701860","title":"Bayesian non-parametric matrix factorization for discovering words in spoken utterances","display_name":"Bayesian non-parametric matrix factorization for discovering words in spoken utterances","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2063385039","doi":"https://doi.org/10.1109/waspaa.2013.6701860","mag":"2063385039"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2013.6701860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","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/A5026428383","display_name":"Sayeh Mirzaei","orcid":"https://orcid.org/0000-0003-1174-2280"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sayeh Mirzaei","raw_affiliation_strings":["Department of Electrical Engineering-ESAT, KU Leuven, Belgium","Dept. of Electr. Eng. ESAT, KU Leuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering-ESAT, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Dept. of Electr. Eng. ESAT, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["Department of Electrical Engineering-ESAT, KU Leuven, Belgium","Dept. of Electr. Eng. ESAT, KU Leuven, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering-ESAT, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Dept. of Electr. Eng. ESAT, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074995295","display_name":"Yaser Norouzi","orcid":"https://orcid.org/0000-0002-9501-889X"},"institutions":[{"id":"https://openalex.org/I158248296","display_name":"Amirkabir University of Technology","ror":"https://ror.org/04gzbav43","country_code":"IR","type":"education","lineage":["https://openalex.org/I158248296"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Yaser Norouzi","raw_affiliation_strings":["Amirkabir University of Technology, Tehran, Iran","Amirkabir University of Technology, Tehran, IRAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amirkabir University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I158248296"]},{"raw_affiliation_string":"Amirkabir University of Technology, Tehran, IRAN","institution_ids":["https://openalex.org/I158248296"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4868,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76624269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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":0.7078971862792969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5398551225662231},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5359227657318115},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5105801224708557},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4955497980117798},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4867003262042999},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.48331356048583984},{"id":"https://openalex.org/keywords/marginal-likelihood","display_name":"Marginal likelihood","score":0.4406258165836334},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.431611567735672},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.41303524374961853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36494243144989014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23097717761993408},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10229659080505371}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078971862792969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5398551225662231},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5359227657318115},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5105801224708557},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4955497980117798},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4867003262042999},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.48331356048583984},{"id":"https://openalex.org/C95923904","wikidata":"https://www.wikidata.org/wiki/Q6760420","display_name":"Marginal likelihood","level":3,"score":0.4406258165836334},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.431611567735672},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.41303524374961853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36494243144989014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23097717761993408},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10229659080505371},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2013.6701860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2013.6701860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/413042","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/123456789/413042/1/3623_final.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE workshop on applications of signal processing to audio and acoustics - WASPAA 2013, New Paltz, New York, USA, 20-23 October 2013","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W148046306","https://openalex.org/W1506806321","https://openalex.org/W1663973292","https://openalex.org/W1963628156","https://openalex.org/W2008565517","https://openalex.org/W2036964623","https://openalex.org/W2113526703","https://openalex.org/W2119239801","https://openalex.org/W2122418603","https://openalex.org/W2147834639","https://openalex.org/W2152131029","https://openalex.org/W2169895393","https://openalex.org/W6681822791"],"related_works":["https://openalex.org/W2016825044","https://openalex.org/W2407375987","https://openalex.org/W2807484975","https://openalex.org/W2505726097","https://openalex.org/W2950975704","https://openalex.org/W2010643158","https://openalex.org/W3049691116","https://openalex.org/W2106867672","https://openalex.org/W4310268968","https://openalex.org/W3081214562"],"abstract_inverted_index":{"In":[0,16],"earlier":[1],"work,":[2,19],"we":[3,20,64],"have":[4],"formulated":[5],"word":[6,76,126],"discovery":[7],"from":[8,137],"speech":[9,168],"as":[10,128,130,164,166],"a":[11,22,66,89,99,118,138,147],"latent":[12,81,93],"component":[13],"analysis":[14],"problem.":[15],"more":[17],"recent":[18],"proposed":[21],"Bayesian":[23,67,142],"approach":[24,69,153],"for":[25,40,54,95,112],"estimating":[26],"the":[27,31,37,49,60,72,96,103,113,131,151],"model":[28,97,123,132,157],"order,":[29],"i.e.":[30],"vocabulary":[32],"size,":[33],"by":[34],"evaluation":[35],"of":[36,80,92,106,121,154],"marginal":[38],"likelihood":[39],"different":[41],"order":[42,56,133],"values.":[43],"That":[44],"technique":[45],"was":[46],"expensive":[47],"since":[48],"algorithm":[50],"should":[51],"be":[52,84],"repeated":[53],"several":[55],"values":[57],"to":[58,70,117],"estimate":[59],"proper":[61],"order.":[62],"Here,":[63],"develop":[65],"non-parametric":[68],"decompose":[71],"spoken":[73],"utterances":[74],"into":[75],"models.":[77],"The":[78,125],"number":[79,91,120],"components":[82,94],"can":[83],"automatically":[85],"discovered":[86],"through":[87],"taking":[88],"large":[90],"and":[98],"weight":[100],"vector":[101],"representing":[102],"overall":[104],"gain":[105,114],"each":[107],"component.":[108],"A":[109],"sparse":[110],"prior":[111],"parameters":[115],"lead":[116],"limited":[119],"activated":[122],"components.":[124],"representations":[127],"well":[129,165],"are":[134,160],"then":[135],"obtained":[136],"single":[139],"iterative":[140],"variational":[141],"inference":[143],"procedure,":[144],"which":[145],"constitutes":[146],"substantial":[148],"advantage":[149],"over":[150],"previous":[152],"trying":[155],"multiple":[156],"orders.":[158],"Experiments":[159],"performed":[161],"on":[162],"synthetic":[163],"real":[167],"data.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}