{"id":"https://openalex.org/W2117305059","doi":"https://doi.org/10.1109/icassp.2008.4518548","title":"HMM adaptation using a phase-sensitive acoustic distortion model for environment-robust speech recognition","display_name":"HMM adaptation using a phase-sensitive acoustic distortion model for environment-robust speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2117305059","doi":"https://doi.org/10.1109/icassp.2008.4518548","mag":"2117305059"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518548","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107639889","display_name":"Yifan Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111957484","display_name":"Alex Acero","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Acero","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA","Microsoft Corporation, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100365053"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":3.81,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.94444444,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4069","last_page":"4072"},"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":0.9997000098228455,"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":0.9937999844551086,"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":0.841006875038147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.74711012840271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6837719678878784},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6531221270561218},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5023412704467773},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48679062724113464},{"id":"https://openalex.org/keywords/nonlinear-distortion","display_name":"Nonlinear distortion","score":0.48351719975471497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4401226043701172},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42917001247406006},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4233744442462921},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08641371130943298}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.841006875038147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74711012840271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6837719678878784},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6531221270561218},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5023412704467773},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48679062724113464},{"id":"https://openalex.org/C173413354","wikidata":"https://www.wikidata.org/wiki/Q7049470","display_name":"Nonlinear distortion","level":4,"score":0.48351719975471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4401226043701172},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42917001247406006},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4233744442462921},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08641371130943298},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2008.4518548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518548","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.187.5463","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.187.5463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/78297/2008-jinyu-icassp2.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.489.4666","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.489.4666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/en-us/um/redmond/groups/srg/papers/2008-deng-icassp.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.851.7626","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.851.7626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/163049/phase.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.855.8038","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.855.8038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/163818/icassp08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1517348348","https://openalex.org/W1562942088","https://openalex.org/W1573570773","https://openalex.org/W1665196592","https://openalex.org/W2009802208","https://openalex.org/W2010023285","https://openalex.org/W2106714211","https://openalex.org/W2136386449","https://openalex.org/W2137401359","https://openalex.org/W2151484683","https://openalex.org/W6630687167","https://openalex.org/W6634340323"],"related_works":["https://openalex.org/W2359780122","https://openalex.org/W2298863895","https://openalex.org/W2001689509","https://openalex.org/W2391717006","https://openalex.org/W1492601442","https://openalex.org/W2187246476","https://openalex.org/W2358330745","https://openalex.org/W4386414661","https://openalex.org/W1599289444","https://openalex.org/W2347431113"],"abstract_inverted_index":{"In":[0,52,94,128],"this":[1,169],"paper,":[2],"we":[3],"present":[4],"a":[5,34],"new":[6,28,140],"approach":[7,29],"to":[8,106,193],"HMM":[9,116,149,157,173],"adaptation":[10],"that":[11,41,179],"jointly":[12],"compensates":[13],"for":[14,155],"additive":[15],"and":[16,48,63,69,84,101,111,118],"convolutive":[17],"acoustic":[18,39,125],"distortion":[19,40,126],"in":[20,74,165,186],"environment-robust":[21],"speech":[22,47,80],"recognition.":[23],"The":[24,175],"hallmark":[25],"of":[26,33,38,56,66,114],"our":[27],"is":[30],"the":[31,49,53,57,61,67,75,79,85,90,95,98,109,115,122,129,133,138,146,152,161,166,180,194],"use":[32],"nonlinear,":[35],"phase-sensitive":[36,92,124],"model":[37],"captures":[42],"phase":[43,181],"asynchrony":[44],"between":[45],"clean":[46],"mixing":[50],"noise.":[51],"first":[54],"step":[55],"developed":[58],"algorithm,":[59],"both":[60],"static":[62,110],"dynamic":[64,112],"portions":[65,113],"noise":[68,100],"channel":[70,102],"parameters":[71,103],"are":[72,104],"estimated":[73,99],"cepstral":[76],"domain,":[77],"using":[78,121,132,145],"recognizer\u2019s":[81],"\u201cfeedback\u201d":[82],"information":[83],"vector-Taylor-series":[86],"linearization":[87],"technique":[88],"on":[89,168],"nonlinear":[91],"model.":[93,127,174],"second":[96],"step,":[97],"used":[105],"effectively":[107],"adapt":[108],"means":[117],"variances":[119],"also":[120],"linearized":[123],"experimental":[130,176],"evaluation":[131],"standard":[134],"Aurora":[135],"2":[136],"task,":[137],"proposed":[139],"algorithm":[141],"achieves":[142],"93.3%":[143],"accuracy":[144],"clean-trained":[147,172],"complex":[148],"backend":[150],"as":[151],"baseline":[153],"system":[154],"unsupervised":[156],"adaptation.":[158],"This":[159],"reaches":[160],"highest":[162],"performance":[163],"number":[164],"literature":[167],"task":[170],"with":[171],"results":[177],"show":[178],"term,":[182],"which":[183],"was":[184],"missing":[185],"all":[187],"previous":[188],"HMM-adaptation":[189],"work,":[190],"contributes":[191],"significantly":[192],"achieved":[195],"high":[196],"recognition":[197],"accuracy.":[198]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}