{"id":"https://openalex.org/W2144271355","doi":"https://doi.org/10.1109/asru.2009.5373446","title":"Hierarchical variational loopy belief propagation for multi-talker speech recognition","display_name":"Hierarchical variational loopy belief propagation for multi-talker speech recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2144271355","doi":"https://doi.org/10.1109/asru.2009.5373446","mag":"2144271355"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5088753951","display_name":"Steven J. Rennie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven J. Rennie","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T J Watson Research Center, Yorktown Heights, N.Y., U.S.A"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T J Watson Research Center, Yorktown Heights, N.Y., U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T J Watson Research Center, Yorktown Heights, N.Y., U.S.A"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T J Watson Research Center, Yorktown Heights, N.Y., U.S.A","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037212510","display_name":"Peder A. Olsen","orcid":"https://orcid.org/0000-0002-3836-8017"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peder A. Olsen","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM T J Watson Research Center, Yorktown Heights, N.Y., U.S.A"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T J Watson Research Center, Yorktown Heights, N.Y., U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088753951"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":2.1148,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87538899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"181"},"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":0.9995999932289124,"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/T11447","display_name":"Blind Source Separation Techniques","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"}}],"keywords":[{"id":"https://openalex.org/keywords/belief-propagation","display_name":"Belief propagation","score":0.7321547865867615},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7261520028114319},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.6052758097648621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5923746228218079},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5225728750228882},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45192524790763855},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4516654312610626},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.44792789220809937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4283146858215332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3969036340713501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39137664437294006},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2667921185493469}],"concepts":[{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.7321547865867615},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7261520028114319},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.6052758097648621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5923746228218079},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5225728750228882},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45192524790763855},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4516654312610626},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.44792789220809937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4283146858215332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3969036340713501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39137664437294006},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2667921185493469},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1800365115","https://openalex.org/W2033178790","https://openalex.org/W2059833849","https://openalex.org/W2060822897","https://openalex.org/W2079362249","https://openalex.org/W2109886546","https://openalex.org/W2112065929","https://openalex.org/W2112921197","https://openalex.org/W2130322773","https://openalex.org/W2150833111","https://openalex.org/W6670689932"],"related_works":["https://openalex.org/W4388627352","https://openalex.org/W4297812452","https://openalex.org/W959529772","https://openalex.org/W2962950510","https://openalex.org/W2153267847","https://openalex.org/W4286382505","https://openalex.org/W2562956507","https://openalex.org/W3180766726","https://openalex.org/W1520194733","https://openalex.org/W2501500329"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,10,36,60],"new":[3],"method":[4,28],"for":[5],"multi-talker":[6],"speech":[7,119],"recognition":[8],"using":[9,32,95,140,160],"single-channel":[11],"that":[12,125],"combines":[13],"loopy":[14],"belief":[15],"propagation":[16],"and":[17,42,84,107],"variational":[18,129],"inference":[19,88,94,109],"methods":[20],"to":[21,47,53,66],"control":[22],"the":[23,44,50,68,75,80,82,96,101,117,126,151],"complexity":[24,85],"of":[25,39,62,79,86,103],"inference.":[26],"The":[27],"models":[29],"each":[30],"source":[31],"an":[33],"HMM":[34],"with":[35,100,112,150],"hierarchical":[37,76,128],"set":[38,61],"acoustic":[40,77,87],"states,":[41],"uses":[43],"max":[45],"model":[46],"approximate":[48],"how":[49],"sources":[51],"interact":[52],"generate":[54],"mixed":[55],"data.":[56],"Inference":[57],"involves":[58],"inferring":[59],"probabilistic":[63,104],"time-frequency":[64,105,164],"masks":[65,73],"separate":[67],"speakers.":[69],"By":[70],"conditioning":[71],"these":[72],"on":[74,116],"states":[78],"speakers,":[81],"fidelity":[83],"can":[89],"be":[90],"precisely":[91],"controlled.":[92],"Acoustic":[93],"algorithm":[97,132],"scales":[98,110],"linearly":[99,111],"number":[102],"masks,":[106],"temporal":[108],"LM":[113],"size.":[114],"Results":[115],"monaural":[118],"separation":[120],"task":[121],"(SSC)":[122],"data":[123],"demonstrate":[124],"presented":[127],"max-sum":[130],"product":[131],"(HVMSP)":[133],"outperforms":[134],"VMSP":[135],"by":[136],"over":[137],"2%":[138],"absolute":[139],"4":[141],"times":[142,162],"fewer":[143],"probablistic":[144],"masks.":[145,165],"HVMSP":[146],"furthermore":[147],"performs":[148],"on-par":[149],"MSP":[152],"algorithm,":[153],"which":[154],"utilizes":[155],"exact":[156],"conditional":[157],"marginal":[158],"likelihoods,":[159],"256":[161],"less":[163]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}