{"id":"https://openalex.org/W2402848636","doi":"https://doi.org/10.21437/interspeech.2015-247","title":"Bayesian integration of sound source separation and speech recognition: a new approach to simultaneous speech recognition","display_name":"Bayesian integration of sound source separation and speech recognition: a new approach to simultaneous speech recognition","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2402848636","doi":"https://doi.org/10.21437/interspeech.2015-247","mag":"2402848636"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-247","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-247","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":"conference-paper","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/A5073445085","display_name":"Kousuke Itakura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kousuke Itakura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055822133","display_name":"Izaya Nishimuta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Izaya Nishimuta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007353694","display_name":"Yoshiaki Bando","orcid":"https://orcid.org/0000-0002-3934-0745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshiaki Bando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998000264167786,"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":0.9986000061035156,"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/speech-recognition","display_name":"Speech recognition","score":0.7719641923904419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264981865882874},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5682686567306519},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5573465824127197},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4975903332233429},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.46309733390808105},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.46091440320014954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3897896707057953},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3655024766921997},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3651444911956787},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21213015913963318}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7719641923904419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264981865882874},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5682686567306519},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5573465824127197},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4975903332233429},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.46309733390808105},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.46091440320014954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3897896707057953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3655024766921997},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3651444911956787},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21213015913963318},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-247","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-247","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.3312","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.3312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/%7Eyoshii/papers/interspeech-2015-itakura.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W27705273","https://openalex.org/W72347498","https://openalex.org/W76407144","https://openalex.org/W109581973","https://openalex.org/W161810042","https://openalex.org/W1582614941","https://openalex.org/W1904457459","https://openalex.org/W2013331954","https://openalex.org/W2062164080","https://openalex.org/W2069432516","https://openalex.org/W2072184010","https://openalex.org/W2088344661","https://openalex.org/W2121348175","https://openalex.org/W2133869761","https://openalex.org/W2141411743","https://openalex.org/W2148719987","https://openalex.org/W2153999007","https://openalex.org/W2160815625","https://openalex.org/W2402404264","https://openalex.org/W2406355448"],"related_works":["https://openalex.org/W2556771176","https://openalex.org/W2640905660","https://openalex.org/W2402949781","https://openalex.org/W1955848339","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,98,118,138],"novel":[4],"Bayesian":[5,99,193],"method":[6,83,152,179],"that":[7,64,155,171],"can":[8],"directly":[9],"recognize":[10],"overlapping":[11],"utterances":[12],"without":[13],"explicitly":[14],"separating":[15],"mixture":[16],"signals":[17,42,89,115],"into":[18],"their":[19],"independent":[20],"components":[21],"in":[22,34,97,172],"advance":[23],"of":[24,43,55,59,67,76,104,112,129,165,174],"speech":[25,32,68,88,95,114,162,167,188],"recognition.":[26],"The":[27],"conventional":[28,182],"approach":[29,62],"to":[30,147,149],"contami-nated":[31],"recognition":[33,69,96,168],"real":[35],"environments":[36],"uniquely":[37],"extracts":[38],"the":[39,56,65,74,109,126,150,177],"clean":[40],"isolated":[41,87,113],"individual":[44],"sources":[45],"(e.g.,":[46],"by":[47,73,90,116],"noise":[48],"reduction,":[49],"dereverberation,":[50],"and":[51,94,124],"source":[52,92,191],"separation).":[53],"One":[54],"main":[57],"limitations":[58],"this":[60,80,141],"cascading":[61,183],"is":[63,70,145],"accuracy":[66,75,176],"upper":[71],"bounded":[72],"pre-processing.":[77],"To":[78],"overcome":[79],"limitation,":[81],"our":[82],"marginal-izes":[84],"out":[85],"uncertain":[86],"integrating":[91],"separation":[93],"manner.":[100],"A":[101],"suf-ficient":[102],"number":[103],"samples":[105,134],"are":[106,135],"drawn":[107],"from":[108,160],"posterior":[110,127],"distribu-tion":[111],"using":[117],"Markov":[119],"chain":[120],"Monte":[121,142],"Carlo":[122,143],"method,":[123],"then":[125],"distributions":[128],"uttered":[130],"texts":[131,158],"for":[132],"those":[133],"integrated.":[136],"Under":[137],"certain":[139],"con-dition,":[140],"integration":[144],"shown":[146],"reduce":[148],"well-known":[151],"called":[153],"ROVER":[154,196],"integrates":[156],"recognized":[157],"obtained":[159],"sampled":[161],"signals.":[163],"Results":[164],"simulta-neous":[166],"experiments":[169],"showed":[170],"terms":[173],"word":[175],"proposed":[178],"significantly":[180],"outperformed":[181],"methods.":[184],"Index":[185],"Terms:":[186],"simultaneous":[187],"recognition,":[189],"sound":[190],"separation,":[192],"modeling,":[194],"MCMC,":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}