{"id":"https://openalex.org/W2964182776","doi":"https://doi.org/10.21437/interspeech.2015-285","title":"Maximum a posteriori adaptation of network parameters in deep models","display_name":"Maximum a posteriori adaptation of network parameters in deep models","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2964182776","doi":"https://doi.org/10.21437/interspeech.2015-285","mag":"2964182776"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-285","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-285","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":"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/A5101472289","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0002-1772-7674"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Huang","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[{"id":"https://openalex.org/I246010334","display_name":"Universit\u00e0 degli Studi di Enna Kore","ror":"https://ror.org/04vd28p53","country_code":"IT","type":"education","lineage":["https://openalex.org/I246010334"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":["Kore University of Enna"],"affiliations":[{"raw_affiliation_string":"Kore University of Enna","institution_ids":["https://openalex.org/I246010334"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605612","display_name":"I\u2010Ming Chen","orcid":"https://orcid.org/0000-0002-4831-3781"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Fan Chen","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934751","display_name":"Jiadong Wu","orcid":"https://orcid.org/0000-0002-0626-4870"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiadong Wu","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066868860","display_name":"Chin\u2010Hui Lee","orcid":"https://orcid.org/0000-0002-1892-2551"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Hui Lee","raw_affiliation_strings":["#N#\u2021#N#Georgia Institute of Technology#N#"],"affiliations":[{"raw_affiliation_string":"#N#\u2021#N#Georgia Institute of Technology#N#","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101472289"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":9.4918,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.97987809,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1076","last_page":"1080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9976000189781189,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.7961917519569397},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7917664051055908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507121562957764},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6235597729682922},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6142817139625549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6096280813217163},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5086737275123596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4955943822860718},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48771223425865173},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4724940359592438},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.46093645691871643},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4552447199821472},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.445893794298172},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4135613441467285},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3954451382160187},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.19458967447280884},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11231294274330139},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07537218928337097}],"concepts":[{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.7961917519569397},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7917664051055908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507121562957764},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6235597729682922},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6142817139625549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6096280813217163},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5086737275123596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4955943822860718},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48771223425865173},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4724940359592438},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.46093645691871643},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4552447199821472},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.445893794298172},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4135613441467285},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3954451382160187},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.19458967447280884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11231294274330139},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07537218928337097},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-285","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-285","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W185613617","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1964863507","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2036351241","https://openalex.org/W2056738732","https://openalex.org/W2058641082","https://openalex.org/W2076794394","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2095168618","https://openalex.org/W2100495367","https://openalex.org/W2100969003","https://openalex.org/W2107215754","https://openalex.org/W2112021726","https://openalex.org/W2117239706","https://openalex.org/W2125838338","https://openalex.org/W2131342762","https://openalex.org/W2136360692","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2147786979","https://openalex.org/W2147794814","https://openalex.org/W2149175990","https://openalex.org/W2160306971","https://openalex.org/W2160373860","https://openalex.org/W2162042984","https://openalex.org/W2187166234","https://openalex.org/W2188305289","https://openalex.org/W2294543795","https://openalex.org/W2403731734","https://openalex.org/W3162418253"],"related_works":["https://openalex.org/W1595191759","https://openalex.org/W2150865841","https://openalex.org/W2010299594","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W2138865713","https://openalex.org/W2169353922","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290"],"abstract_inverted_index":{"We":[0,48],"present":[1,130],"a":[2,9,32,51,58],"Bayesian":[3],"approach":[4,112],"to":[5,17,69,79,134,138],"adapting":[6],"parameters":[7,28,56],"of":[8,26,35,39,55,57,101],"well-trained":[10],"context-dependent,":[11],"deep-neural-network,":[12],"hidden":[13,66],"Markov":[14],"model":[15,43],"(CD-DNN-HMM)":[16],"improve":[18,139],"automatic":[19],"speech":[20],"recognition":[21],"performance.":[22],"Given":[23],"an":[24,63,131],"abundance":[25],"DNN":[27,42],"but":[29],"with":[30,62,144],"only":[31],"limited":[33,145],"amount":[34],"data,":[36],"the":[37,40,70,90,99,102,108,123],"effectiveness":[38,143],"adapted":[41],"can":[44],"often":[45],"be":[46],"compromised.":[47],"formulate":[49],"maximum":[50],"posteriori":[52],"(MAP)":[53],"adaptation":[54,111,140,146],"specially":[59],"designed":[60],"CD-DNN-HMM":[61],"augmented":[64],"linear":[65,83],"networks":[67],"connected":[68],"output":[71],"tied":[72],"states,":[73],"or":[74],"senones,":[75],"and":[76,120,142],"compare":[77],"it":[78],"feature":[80],"space":[81],"MAP":[82,110],"regression":[84],"previously":[85],"proposed.":[86],"Experimental":[87],"evidences":[88],"on":[89],"20,000-word":[91],"open":[92],"vocabulary":[93],"Wall":[94],"Street":[95],"Journal":[96],"task":[97],"demonstrate":[98],"feasibility":[100],"proposed":[103,109],"framework.":[104],"In":[105],"supervised":[106],"adaptation,":[107],"provides":[113],"more":[114],"than":[115],"10%":[116],"relative":[117],"error":[118],"reduction":[119],"consistently":[121],"outperforms":[122],"conventional":[124],"transformation":[125],"based":[126],"methods.":[127],"Furthermore,":[128],"we":[129],"initial":[132],"attempt":[133],"generate":[135],"hierarchical":[136],"priors":[137],"efficiency":[141],"data":[147],"by":[148],"exploiting":[149],"similarities":[150],"among":[151],"senones.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}