{"id":"https://openalex.org/W1545418955","doi":"https://doi.org/10.21437/interspeech.2011-39","title":"Phonological knowledge guided HMM state mapping for cross-lingual speaker adaptation","display_name":"Phonological knowledge guided HMM state mapping for cross-lingual speaker adaptation","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W1545418955","doi":"https://doi.org/10.21437/interspeech.2011-39","mag":"1545418955"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/167431","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068810492","display_name":"Hui Liang","orcid":"https://orcid.org/0000-0001-6632-0929"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Hui Liang","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["IDIAP research institute"],"affiliations":[{"raw_affiliation_string":"IDIAP research institute","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068810492"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":3.0817,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9152897,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1825","last_page":"1828"},"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":0.9983999729156494,"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":0.9945999979972839,"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":0.7310126423835754},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7049607038497925},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6585187315940857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6331267952919006},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.6046593189239502},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5386663675308228},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5189830660820007},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5174258947372437},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5119093656539917},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5017588138580322},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5005197525024414},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4828503727912903},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40463265776634216},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3979354500770569},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33755895495414734},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1154387891292572},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1076560914516449},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10575920343399048}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7310126423835754},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7049607038497925},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6585187315940857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6331267952919006},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.6046593189239502},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5386663675308228},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5189830660820007},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5174258947372437},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5119093656539917},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5017588138580322},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5005197525024414},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4828503727912903},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40463265776634216},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3979354500770569},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33755895495414734},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1154387891292572},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1076560914516449},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10575920343399048},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2011-39","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-39","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:167431","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/167431","pdf_url":"http://infoscience.epfl.ch/record/167431","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"http://infoscience.epfl.ch/record/167431","raw_type":"Text"},{"id":"pmh:oai:infoscience.tind.io:167432","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/69410","pdf_url":"http://publications.idiap.ch/index.php/publications/showcite/Liang_INTERSPEECH_2011","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"report"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.1040","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.1040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2011/Liang_INTERSPEECH_2011.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:167432","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/167432","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:167431","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/167431","pdf_url":"http://infoscience.epfl.ch/record/167431","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"http://infoscience.epfl.ch/record/167431","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1545418955.pdf","grobid_xml":"https://content.openalex.org/works/W1545418955.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W113498433","https://openalex.org/W128185859","https://openalex.org/W1660564604","https://openalex.org/W1984905644","https://openalex.org/W2019395288","https://openalex.org/W2049686551","https://openalex.org/W2114010348","https://openalex.org/W2117418893","https://openalex.org/W2139751012","https://openalex.org/W2149270762","https://openalex.org/W2153914468","https://openalex.org/W2158069733","https://openalex.org/W4390926366"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W2206035908","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W1616881371","https://openalex.org/W1520875569","https://openalex.org/W2199957582"],"abstract_inverted_index":{"Within":[0],"the":[1,9,20,58,65,87],"HMM":[2],"state":[3,26,33,62],"mapping-based":[4],"cross-lingual":[5,130],"speaker":[6,109,131],"adaptation":[7],"framework,":[8],"minimum":[10,127],"Kullback-Leibler":[11],"divergence":[12],"criterion":[13,40],"has":[14],"been":[15],"typically":[16],"employed":[17],"to":[18,56,71,111],"measure":[19],"similarity":[21],"of":[22,86,91,97],"two":[23,29,66],"average":[24],"voice":[25],"distributions":[27,63],"from":[28,64,105],"respective":[30],"languages":[31,67],"for":[32],"mapping":[34,59,79,102],"construction.":[35],"Considering":[36],"that":[37,101],"this":[38],"simple":[39],"doesn\u2019t":[41],"take":[42],"any":[43],"language-specific":[44],"information":[45],"into":[46],"account,":[47],"we":[48],"propose":[49],"a":[50,106],"data-driven,":[51],"phonological":[52,125],"knowledge":[53],"guided":[54],"approach":[55,94],"strengthen":[57],"construction":[60],"\u2013":[61],"are":[68,81],"clustered":[69],"according":[70],"broad":[72],"phonetic":[73],"categories":[74],"using":[75],"decision":[76],"trees":[77],"and":[78,100],"rules":[80,103],"constructed":[82],"only":[83],"within":[84],"each":[85],"clusters.":[88],"Objective":[89],"evaluation":[90],"our":[92],"proposed":[93],"demonstrates":[95],"reduction":[96],"mel-cepstral":[98],"distortion":[99],"derived":[104],"single":[107],"training":[108],"generalize":[110],"other":[112],"speakers,":[113],"with":[114],"subtle":[115],"improvement":[116],"being":[117],"detected":[118],"during":[119],"subjective":[120],"listening":[121],"tests.":[122],"Index":[123],"Terms:":[124],"knowledge,":[126],"generation":[128],"error,":[129],"adaptation,":[132],"HMM-based":[133],"TTS":[134]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
