{"id":"https://openalex.org/W2109886546","doi":"https://doi.org/10.1109/icassp.2009.4960466","title":"Single-channel speech separation and recognition using loopy belief propagation","display_name":"Single-channel speech separation and recognition using loopy belief propagation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2109886546","doi":"https://doi.org/10.1109/icassp.2009.4960466","mag":"2109886546"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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":false,"raw_author_name":"Steven J. Rennie","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3845","last_page":"3848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9994000196456909,"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":0.9987999796867371,"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":0.9987999796867371,"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/belief-propagation","display_name":"Belief propagation","score":0.8425009250640869},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7138640284538269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7120382189750671},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5936842560768127},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.5856663584709167},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5747418403625488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.562086820602417},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.5582126975059509},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5371795892715454},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4944941997528076},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.442039430141449},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4311668872833252},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4155632257461548},{"id":"https://openalex.org/keywords/grammar-induction","display_name":"Grammar induction","score":0.4150769114494324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3781459927558899},{"id":"https://openalex.org/keywords/rule-based-machine-translation","display_name":"Rule-based machine translation","score":0.3764970898628235},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.1811365783214569}],"concepts":[{"id":"https://openalex.org/C152948882","wikidata":"https://www.wikidata.org/wiki/Q4060686","display_name":"Belief propagation","level":3,"score":0.8425009250640869},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7138640284538269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120382189750671},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5936842560768127},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.5856663584709167},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5747418403625488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.562086820602417},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.5582126975059509},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5371795892715454},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4944941997528076},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.442039430141449},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4311668872833252},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4155632257461548},{"id":"https://openalex.org/C56601403","wikidata":"https://www.wikidata.org/wiki/Q5593673","display_name":"Grammar induction","level":3,"score":0.4150769114494324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3781459927558899},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.3764970898628235},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.1811365783214569},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960466","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1566152912","https://openalex.org/W1800365115","https://openalex.org/W2059833849","https://openalex.org/W2060822897","https://openalex.org/W2098387242","https://openalex.org/W2112089769","https://openalex.org/W2112921197","https://openalex.org/W2130322773","https://openalex.org/W2137813581","https://openalex.org/W2159938933","https://openalex.org/W6676877154","https://openalex.org/W6683716525"],"related_works":["https://openalex.org/W2962950510","https://openalex.org/W2153267847","https://openalex.org/W2293346268","https://openalex.org/W2904254030","https://openalex.org/W2097107341","https://openalex.org/W2161508606","https://openalex.org/W4297779426","https://openalex.org/W2109849264","https://openalex.org/W2109886546","https://openalex.org/W2131513205"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,63,81,108],"problem":[3],"of":[4,25,32,35,40,71,76,110,134,140],"single-channel":[5],"speech":[6,26],"separation":[7],"and":[8,136],"recognition":[9],"using":[10,85,99],"loopy":[11,118],"belief":[12],"propagation":[13],"in":[14,80,92],"a":[15,33,43,49,94,117],"way":[16],"that":[17,104,122],"enables":[18],"efficient":[19],"inference":[20,91],"for":[21,48,67,146],"an":[22,100,138],"arbitrary":[23],"number":[24,109],"sources.":[27,111],"The":[28,74,129],"graphical":[29],"model":[30,45,55,62,95,127],"consists":[31],"set":[34],"N":[36],"Markov":[37],"chains,":[38],"each":[39,68,72],"which":[41],"represents":[42],"language":[44,126],"or":[46],"grammar":[47,69],"given":[50],"speaker.":[51],"A":[52],"Gaussian":[53],"mixture":[54],"with":[56,107,125],"shared":[57],"states":[58],"is":[59,78,137],"used":[60],"to":[61],"hidden":[64],"acoustic":[65],"signal":[66],"state":[70],"source.":[73],"combination":[75],"sources":[77],"modeled":[79],"log":[82],"spectrum":[83],"domain":[84],"non-linear":[86],"interaction":[87],"functions.":[88],"Previously,":[89],"temporal":[90],"such":[93],"has":[96],"been":[97],"performed":[98],"N-dimensional":[101],"Viterbi":[102],"algorithm":[103,121,130],"scales":[105,123],"exponentially":[106],"In":[112],"this":[113],"paper,":[114],"we":[115],"describe":[116],"message":[119],"passing":[120],"linearly":[124],"size.":[128],"achieves":[131],"human":[132],"levels":[133],"performance,":[135],"order":[139],"magnitude":[141],"faster":[142],"than":[143],"competitive":[144],"systems":[145],"two":[147],"speakers.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}