{"id":"https://openalex.org/W2102362163","doi":"https://doi.org/10.1109/icassp.2008.4518614","title":"Adaptation of compressed HMM parameters for resource-constrained speech recognition","display_name":"Adaptation of compressed HMM parameters for resource-constrained speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2102362163","doi":"https://doi.org/10.1109/icassp.2008.4518614","mag":"2102362163"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518614","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/A5101674460","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0002-3101-7011"},"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":"Jian Wu","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/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"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":6,"corresponding_author_ids":["https://openalex.org/A5100365053"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.7745,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67901235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4333","last_page":"4336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7782657742500305},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7183976173400879},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6659736037254333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.644009530544281},{"id":"https://openalex.org/keywords/uncompressed-video","display_name":"Uncompressed video","score":0.618401050567627},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.474293977022171},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46379950642585754},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.45182156562805176},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4108160734176636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40136033296585083},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16182807087898254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7782657742500305},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7183976173400879},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6659736037254333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.644009530544281},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.618401050567627},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.474293977022171},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46379950642585754},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.45182156562805176},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4108160734176636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40136033296585083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16182807087898254},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2008.4518614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518614","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:10.1.1.188.374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.188.374","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/78270/2008-jinyu-icassp.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.543.8153","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.543.8153","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-icasspb.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1665196592","https://openalex.org/W2010023285","https://openalex.org/W2100969003","https://openalex.org/W2111612810","https://openalex.org/W2136386449","https://openalex.org/W2142873456","https://openalex.org/W2146871184","https://openalex.org/W2151484683","https://openalex.org/W2155445312"],"related_works":["https://openalex.org/W4244492201","https://openalex.org/W2165546027","https://openalex.org/W2112348346","https://openalex.org/W1992053816","https://openalex.org/W2380813680","https://openalex.org/W4297785055","https://openalex.org/W2405812711","https://openalex.org/W2776275422","https://openalex.org/W2370128788","https://openalex.org/W1523010715"],"abstract_inverted_index":{"Recently,":[0],"we":[1,37],"successfully":[2],"developed":[3,66],"and":[4,17,67,87,105,112,120,138,169,198],"reported":[5],"a":[6,177],"new":[7],"unsupervised":[8],"online":[9],"adaptation":[10],"technique,":[11],"which":[12,142],"jointly":[13],"compensates":[14],"for":[15,55],"additive":[16],"convolutive":[18],"distortions":[19],"with":[20,92,151],"vector":[21],"Taylor":[22],"series":[23],"(JAC/VTS),":[24],"to":[25,41,69],"adjust":[26],"(uncompressed)":[27],"HMMs":[28,44],"under":[29],"acoustically":[30],"distorted":[31],"environments":[32],"[1].":[33],"In":[34],"this":[35],"paper,":[36],"extend":[38],"that":[39,89],"technique":[40],"adapt":[42],"compressed":[43,79],"using":[45],"JAC/VTS":[46],"where":[47,94],"limited":[48],"computation":[49,167,196],"and/or":[50],"memory":[51,174,203],"resources":[52],"are":[53,85,100,118],"available":[54],"speech":[56,128],"recognition":[57,103,207],"(e.g.,":[58],"on":[59,122],"mobile":[60],"devices).":[61],"Subspace":[62],"coding":[63],"(SSC)":[64],"is":[65,143],"used":[68],"quantize":[70],"each":[71],"dimension":[72],"of":[73,98,114,126,165,172,181,184,194,201],"the":[74,78,106,123,135,144,147,155,166,173,195,202],"multivariate":[75],"Gaussians":[76],"in":[77,154],"HMMs.":[80],"Three":[81],"algorithmic":[82],"design":[83],"options":[84,117],"proposed":[86],"evaluated":[88],"combine":[90],"SSC":[91],"JAC/VTS,":[93],"three":[95,116],"different":[96],"types":[97],"tradeoffs":[99],"made":[101],"between":[102],"accuracy":[104,149,185,208],"required":[107],"computation/memory/storage":[108],"resources.":[109],"The":[110,130,159,188],"strengths":[111],"weaknesses":[113],"these":[115],"discussed":[119],"shown":[121],"Aurora2":[124],"task":[125],"noise-robust":[127],"recognition.":[129],"first":[131],"option":[132,161,190],"greatly":[133],"reduces":[134,162],"storage":[136],"space":[137],"gives":[139],"93.2%":[140],"accuracy,":[141],"same":[145],"as":[146],"baseline":[148],"but":[150],"little":[152],"reduction":[153],"run-time":[156],"computation/memory":[157],"cost.":[158],"second":[160],"about":[163,170,192,199],"79.9%":[164],"cost":[168,197],"33.5%":[171],"requirement":[175,204],"at":[176],"very":[178],"small":[179],"price":[180],"0.5%":[182],"decrease":[183],"(to":[186,211],"92.7%).":[187],"third":[189],"cuts":[191],"89.2%":[193],"65.5%":[200],"while":[205],"reducing":[206],"by":[209],"2.7%":[210],"90.5%).":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}