{"id":"https://openalex.org/W256962426","doi":"https://doi.org/10.21437/interspeech.2006-199","title":"Cross-system adaptation and combination for continuous speech recognition: the influence of phoneme set and acoustic front-end","display_name":"Cross-system adaptation and combination for continuous speech recognition: the influence of phoneme set and acoustic front-end","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W256962426","doi":"https://doi.org/10.21437/interspeech.2006-199","mag":"256962426"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-199","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5065183855","display_name":"Sebastian St\u00fcker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian St\u00fcker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048075735","display_name":"Christian F\u00fcgen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian F\u00fcgen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034672538","display_name":"Susanne Burger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Susanne Burger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064051745","display_name":"Matthias W\u00f6lfel","orcid":"https://orcid.org/0000-0003-1601-5146"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias W\u00f6lfel","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9542,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.85676972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"paper 1509","last_page":"Mon3A2O.2"},"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/T11309","display_name":"Music and Audio Processing","score":0.9902999997138977,"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/T10860","display_name":"Speech and Audio Processing","score":0.9897000193595886,"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/speech-recognition","display_name":"Speech recognition","score":0.7866798043251038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7704230546951294},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6367301940917969},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5789157748222351},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.529040515422821},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5269801616668701},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4908965229988098},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4898959994316101},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47379347681999207},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45469868183135986},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4483088254928589},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4287399649620056},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42047038674354553},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35200706124305725}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7866798043251038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7704230546951294},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6367301940917969},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5789157748222351},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.529040515422821},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5269801616668701},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4908965229988098},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4898959994316101},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47379347681999207},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45469868183135986},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4483088254928589},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4287399649620056},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42047038674354553},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35200706124305725},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"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:10.21437/interspeech.2006-199","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W29040644","https://openalex.org/W29925427","https://openalex.org/W1904457459","https://openalex.org/W2100392285","https://openalex.org/W2112546487","https://openalex.org/W2121017435","https://openalex.org/W2121147010","https://openalex.org/W2134756243","https://openalex.org/W2144639996","https://openalex.org/W2146871184","https://openalex.org/W2161966221","https://openalex.org/W2165871906","https://openalex.org/W2594610113"],"related_works":["https://openalex.org/W2740630172","https://openalex.org/W2400533375","https://openalex.org/W4255044973","https://openalex.org/W2470236000","https://openalex.org/W2097143083","https://openalex.org/W2499802997","https://openalex.org/W2112059504","https://openalex.org/W2727729836","https://openalex.org/W1960256358","https://openalex.org/W2548037963"],"abstract_inverted_index":{"Abstract":[0],"Cross-system":[1],"adaptation":[2,120,127,172],"and":[3,9,60,75,196,231,248],"system":[4,93,99,132,283],"combination":[5],"methods,such":[6],"as":[7],"ROVER":[8],"confusion":[10],"network":[11],"combination,":[12],"areknown":[13],"to":[14,115,133,155,166,235,254],"lower":[15],"the":[16,25,37,53,85,88,131,134,158,164,168,215,219,223,238,240],"word":[17,216],"error":[18],"rate":[19],"of":[20,27,87,121,218,229,246,263],"speech":[21,97,109],"recognitionsystems.":[22],"They":[23],"require":[24],"training":[26],"systems":[28,69,111,118,180],"that":[29,41,84,174],"are":[30,170,181],"rea-sonably":[31],"close":[32],"in":[33,43,161,178,208],"performance":[34],"but":[35],"at":[36],"same":[38],"time":[39],"produceoutput":[40],"differs":[42],"its":[44,267],"errors.":[45],"This":[46,227],"provides":[47],"complemen-taryinformationwhichleadstoperformanceimprovements.In":[48],"this":[49,244],"paper":[50],"we":[51,55],"demonstrate":[52],"gains":[54,272],"have":[56],"seen":[57],"withcross-systemadaptationandsystemcombinationontheEn-glish":[58],"EPPS":[59],"RT0-05S":[61],"lecture":[62],"meeting":[63],"task.":[64],"We":[65],"obtainedthe":[66],"necessary":[67],"varying":[68],"by":[70,280],"using":[71],"different":[72],"acous-tic":[73],"front-ends":[74],"phoneme":[76],"sets":[77],"on":[78,91,266],"which":[79,167],"our":[80],"models":[81,159,169],"arebased.":[82],"Inasetofcontrastiveexperimentsweshowthein\ufb02u-ence":[83],"exchange":[86],"components":[89],"has":[90],"adaptationand":[92],"combination.Index":[94],"Terms:":[95],"automatic":[96,149],"recognition,":[98],"com-bination,":[100],"cross":[101],"adaptation,":[102],"EPPS,":[103],"RT-05S.":[104],"1.":[105],"Introduction":[106],"In":[107],"state-of-the-art":[108],"recognition":[110,241],"it":[112,233],"is":[113,206],"commonpractice":[114],"use":[116],"multi-pass":[117],"with":[119],"theacoustic":[122],"model":[123,188],"in-between":[124],"passes.":[125],"The":[126],"aims":[128],"atbetter":[129],"\ufb01tting":[130],"speakers":[135],"and/or":[136],"acoustic":[137],"en-vironmentsfoundinthetestdata.":[138],"Itisusuallyperformedona":[139],"by-speaker":[140],"basis,":[141],"obtained":[142,221],"either":[143,157],"from":[144,222],"manual":[145],"speaker":[146],"la-bels":[147],"or":[148,260],"clustering":[150],"methods.":[151,204],"Common":[152],"adaptationmethods":[153],"try":[154],"transform":[156],"used":[160],"a":[162,187,282],"systemor":[163],"features":[165],"applied.Three":[171],"methods":[173],"can":[175,273,277],"be":[176,274,278],"found":[177],"manystate-of-the-art":[179],"Maximum":[182],"Likelihood":[183],"LinearRegression":[184],"(MLLR)":[185],"[1],":[186],"transformation,":[189],"Vo-cal":[190],"Tract":[191],"Length":[192],"Normalization":[193],"(VTLN)":[194],"[2]":[195],"feature-space":[197],"constrained":[198],"MLLR":[199],"(fMLLR)":[200],"[3],":[201],"two":[202,259],"feature-transformation":[203],"Adaptation":[205],"performed":[207],"an":[209],"un-supervisedmanner,suchthattheerror-pronehypothesesob-tainedfromthepreviousdecodingpassaretakenasthenec-essary":[210],"reference":[211],"for":[212],"adaptation.":[213],"Generally,":[214],"errorrates":[217],"hypotheses":[220],"adapted":[224],"systemsarelowerthanthoseforhypothesesonwhichtheadaptationwas":[225],"performed.":[226],"sequences":[228],"adaption":[230],"decodingmake":[232],"possible":[234],"incrementally":[236],"improve":[237],"performanceof":[239],"system.":[242],"Unfortunately,":[243],"loop":[245],"adap-tation":[247],"decoding":[249],"does":[250],"not":[251],"always":[252],"lead":[253],"signi\ufb01cant":[255],"im-provements.":[256],"Often,":[257],"after":[258],"three":[261],"stages":[262],"adapting":[264,281],"asystem":[265],"own":[268],"output,":[269],"no":[270],"more":[271],"obtained.This":[275],"problem":[276],"overcome":[279]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}