{"id":"https://openalex.org/W2255778576","doi":"https://doi.org/10.21437/interspeech.2013-733","title":"Accent- and speaker-specific polyphone decision trees for non-native speech recognition","display_name":"Accent- and speaker-specific polyphone decision trees for non-native speech recognition","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2255778576","doi":"https://doi.org/10.21437/interspeech.2013-733","mag":"2255778576"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-733","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5087799432","display_name":"Dominic Telaar","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dominic Telaar","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005148508","display_name":"Mark C. Fuhs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark C. Fuhs","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087799432"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.13997911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3313","last_page":"3316"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.7449458241462708},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6670576333999634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6657684445381165},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6626367568969727},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.605746865272522},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.539923369884491},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5348426699638367},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5324417352676392},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.523306131362915},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.5167700052261353},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5143347978591919},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49950623512268066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4068060517311096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36466336250305176},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1569291651248932}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449458241462708},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6670576333999634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6657684445381165},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6626367568969727},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.605746865272522},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.539923369884491},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5348426699638367},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5324417352676392},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.523306131362915},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.5167700052261353},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5143347978591919},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49950623512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4068060517311096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36466336250305176},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1569291651248932},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-733","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W26182539","https://openalex.org/W1581166685","https://openalex.org/W1956164794","https://openalex.org/W1993499045","https://openalex.org/W2027030707","https://openalex.org/W2162370554","https://openalex.org/W2169883442","https://openalex.org/W2293503202","https://openalex.org/W2407346027"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1197719229","https://openalex.org/W4247736853","https://openalex.org/W2381158726","https://openalex.org/W2552734076","https://openalex.org/W2162158162","https://openalex.org/W106647055","https://openalex.org/W1992796048","https://openalex.org/W1493012537","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Acoustic":[0],"models":[1],"in":[2,45,97,104],"state-of-the-art":[3],"LVCSR":[4],"systems":[5,122,128],"are":[6,41],"typically":[7],"trained":[8],"on":[9,57],"data":[10],"from":[11],"thousands":[12,65],"of":[13,25,64,66,69,73,75,110],"speakers":[14,37,59],"and":[15,28,71,93,144],"then":[16],"adapted":[17],"to":[18,54,86,106,115],"a":[19,81,116,146],"speaker":[20,117,154],"using,":[21],"e.g.,":[22],"various":[23],"combinations":[24],"CMLLR,":[26],"MLLR":[27],"MAP.":[29],"This":[30],"adaptation":[31,155],"step":[32],"is":[33,149],"particularly":[34,150],"important":[35],"for":[36,120,127],"with":[38,61,129],"accents":[39,92],"that":[40],"not":[42],"well":[43],"represented":[44],"the":[46,62,98,108],"training":[47,77,145],"set.":[48],"The":[49],"present":[50],"study":[51],"explores":[52],"how":[53,88],"improve":[55],"performance":[56,142],"South-Asian-accented":[58],"(SoA-accented)":[60],"availability":[63],"US-accented,":[67],"hundreds":[68],"SoA-accented,":[70],"tens":[72],"hours":[74],"speaker-specific":[76],"data.":[78,156],"We":[79],"employ":[80],"decision":[82,99],"tree":[83],"similarity":[84],"measure":[85],"analyze":[87],"varying":[89],"co-articulations":[90],"across":[91],"people":[94],"manifest":[95],"themselves":[96],"tree.":[100],"Modeling":[101],"these":[102],"variations":[103],"addition":[105],"adapting":[107],"GMMs":[109],"an":[111],"existing":[112],"baseline":[113],"system":[114,148],"improved":[118],"WER":[119],"small":[121],"(1k":[123],"GMMs),":[124],"but":[125],"improvement":[126],"larger":[130],"trees":[131],"(2k,":[132],"3k":[133],"GMMs)":[134],"was":[135],"modest.":[136],"Overall,":[137],"GMM":[138],"adaptation/retraining":[139],"yields":[140],"significant":[141],"benefits,":[143],"SoA-accent-specific":[147],"worthwhile":[151],"when":[152],"lacking":[153]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}