{"id":"https://openalex.org/W1581166685","doi":"https://doi.org/10.21437/interspeech.2012-516","title":"Enhanced polyphone decision tree adaptation for accented speech recognition","display_name":"Enhanced polyphone decision tree adaptation for accented speech recognition","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W1581166685","doi":"https://doi.org/10.21437/interspeech.2012-516","mag":"1581166685"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-516","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Enhanced_Polyphone_Decision_Tree_Adaptation_for_Accented_Speech_Recognition/6473357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012623245","display_name":"Udhyakumar Nallasamy","orcid":null},"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":"Udhyakumar Nallasamy","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"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":"Tanja Schultz","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":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.0801,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87514012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1902","last_page":"1905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9983000159263611,"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":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7845869064331055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7061415314674377},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6667144298553467},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.646264910697937},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6005057096481323},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.5951042771339417},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.583756148815155},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5073737502098083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4846978187561035},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4728917181491852},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.44623619318008423},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43626174330711365},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4160323143005371},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3845956325531006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3543124198913574},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2753119468688965},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.20254114270210266},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10229861736297607},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10058817267417908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845869064331055},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7061415314674377},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6667144298553467},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.646264910697937},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6005057096481323},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.5951042771339417},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.583756148815155},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5073737502098083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4846978187561035},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4728917181491852},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.44623619318008423},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43626174330711365},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4160323143005371},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3845956325531006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3543124198913574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2753119468688965},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.20254114270210266},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10229861736297607},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10058817267417908},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2012-516","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-516","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/6473357","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Enhanced_Polyphone_Decision_Tree_Adaptation_for_Accented_Speech_Recognition/6473357","pdf_url":"https://figshare.com/articles/journal_contribution/Enhanced_Polyphone_Decision_Tree_Adaptation_for_Accented_Speech_Recognition/6473357","source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:repository.cmu.edu:lti-1107","is_oa":false,"landing_page_url":"http://repository.cmu.edu/lti/109","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473357","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"doi:10.1184/r1/6473357.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473357.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473357","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Enhanced_Polyphone_Decision_Tree_Adaptation_for_Accented_Speech_Recognition/6473357","pdf_url":"https://figshare.com/articles/journal_contribution/Enhanced_Polyphone_Decision_Tree_Adaptation_for_Accented_Speech_Recognition/6473357","source":{"id":"https://openalex.org/S4306402621","display_name":"INDIGO (University of Illinois at Chicago)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39422238","host_organization_name":"University of Illinois Chicago","host_organization_lineage":["https://openalex.org/I39422238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W1581166685.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W135931203","https://openalex.org/W146813616","https://openalex.org/W1564887926","https://openalex.org/W1578856370","https://openalex.org/W1956164794","https://openalex.org/W2027030707","https://openalex.org/W2077853988","https://openalex.org/W2108872474","https://openalex.org/W2113783933","https://openalex.org/W2144203339","https://openalex.org/W2155770957","https://openalex.org/W2158420521"],"related_works":["https://openalex.org/W1595191759","https://openalex.org/W2010299594","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2121652828"],"abstract_inverted_index":{"State-of-the-art":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"models":[5,42],"struggle":[6],"to":[7,45,70,82,90,145],"handle":[8],"accented":[9],"speech,":[10],"particularly":[11],"if":[12],"the":[13,19,31,46,55,60,72,79,91,97,104],"target":[14],"accent":[15],"is":[16],"under-represented":[17],"in":[18,96],"training":[20],"data.":[21,48],"The":[22],"acoustic":[23],"variations":[24,94],"presented":[25],"by":[26],"an":[27],"unfamiliar":[28],"accent,":[29],"render":[30],"ASR":[32,115],"polyphone":[33,61,139],"decision":[34,62,140],"tree":[35,141],"(PDT)":[36],"and":[37,119,122,134,156],"its":[38],"associated":[39],"Gaussian":[40],"mixture":[41],"(GMM)":[43],"misfit":[44],"test":[47],"In":[49],"this":[50],"paper,":[51],"we":[52,148],"improve":[53],"on":[54,108,117],"previous":[56,136],"work":[57],"of":[58,74,138],"adapting":[59],"tree,":[63],"using":[64],"a":[65,109,135],"semi-continuous":[66],"model":[67],"based":[68,106],"approach":[69],"address":[71],"problem":[73],"data":[75],"sparsity.":[76],"We":[77,113],"extend":[78],"existing":[80],"PDT":[81],"introduce":[83],"additional":[84],"states":[85],"with":[86],"shared":[87],"parameters,":[88],"corresponding":[89],"new":[92],"contextual":[93],"identified":[95],"adaptation":[98,111,133],"data,":[99],"while":[100],"still":[101],"robustly":[102],"estimating":[103],"state":[105],"parameters":[107],"small":[110],"set.":[112],"conduct":[114],"experiments":[116],"Arabic":[118,155],"English":[120],"accents":[121],"show":[123],"that":[124],"our":[125],"technique":[126],"performs":[127],"better":[128],"than":[129],"Maximum":[130],"A-Posteriori":[131],"(MAP)":[132],"implementation":[137],"specialization":[142],"(PDTS).":[143],"Compared":[144],"MAP":[146],"adaptation,":[147],"obtain":[149],"7%":[150],"relative":[151,158],"improvement":[152,159],"for":[153,160],"Dialectal":[154],"13.8%":[157],"Accented":[161],"English.":[162]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}