{"id":"https://openalex.org/W8389927","doi":"https://doi.org/10.21437/interspeech.2005-147","title":"Acoustic and phonetic confusions in accented speech recognition","display_name":"Acoustic and phonetic confusions in accented speech recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W8389927","doi":"https://doi.org/10.21437/interspeech.2005-147","mag":"8389927"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-147","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5100330618","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1399-7420"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3033","last_page":"3036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9988999962806702,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.735287606716156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6797485947608948},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42337143421173096},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.363277792930603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3533240556716919}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.735287606716156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797485947608948},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42337143421173096},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.363277792930603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3533240556716919},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2005-147","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-20435","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-20435","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.116.7229","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.116.7229","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.ust.hk/~pascale/Publications/conference/2005/InterSpeech2005.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W153989523","https://openalex.org/W1516500061","https://openalex.org/W2027116218","https://openalex.org/W2113419766"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Accented":[0],"speech":[1,8,23,82,87,168],"recognition":[2,9,83],"is":[3,29,47,68,141],"more":[4],"challenging":[5],"than":[6],"standard":[7,86,167],"due":[10],"to":[11,37,49,70,79,95,103,145],"the":[12,44],"effects":[13],"of":[14],"phonetic":[15,97,109,123,148],"and":[16,56,72,99,143],"acoustic":[17,101,105,113,127,151],"confusions.":[18],"Phonetic":[19],"confusion":[20,41,114,128,149,152],"in":[21,77,117,154],"accented":[22,81,155],"occurs":[24,42],"when":[25,43],"an":[26,118],"expected":[27],"phone":[28,46],"pronounced":[30,45],"as":[31,61],"a":[32,158],"different":[33],"one,":[34],"which":[35],"leads":[36],"erroneous":[38],"recognition.":[39,88,169],"Acoustic":[40],"found":[48],"lie":[50],"acoustically":[51],"between":[52],"two":[53],"baseform":[54],"models":[55,124],"can":[57],"be":[58],"equally":[59],"recognized":[60],"either":[62],"one.":[63],"We":[64,89],"propose":[65,90],"that":[66,138],"it":[67],"necessary":[69],"analyze":[71],"model":[73],"these":[74],"confusions":[75],"separately":[76],"order":[78],"improve":[80],"without":[84,165],"degrading":[85,166],"using":[91,131],"likelihood":[92],"ratio":[93],"test":[94],"measure":[96,104],"confusion,":[98],"asymmetric":[100],"distance":[102],"confusion.":[106],"Only":[107],"accent-specific":[108],"units":[110],"with":[111,125,157],"low":[112],"are":[115,129],"used":[116],"augmented":[119],"pronunciation":[120],"dictionary,":[121],"while":[122],"high":[126],"reconstructed":[130],"decision":[132],"tree":[133],"merging.":[134],"Experimental":[135],"results":[136],"show":[137],"our":[139],"approach":[140],"effective":[142],"superior":[144],"methods":[146],"modeling":[147],"or":[150],"alone":[153],"speech,":[156],"significant":[159],"5.7":[160],"%":[161],"absolute":[162],"WER":[163],"reduction,":[164],"1.":[170]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
