{"id":"https://openalex.org/W4224861836","doi":"https://doi.org/10.21437/interspeech.2022-10444","title":"Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition","display_name":"Linguistic-Acoustic Similarity Based Accent Shift for Accent Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224861836","doi":"https://doi.org/10.21437/interspeech.2022-10444"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10444","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5018773485","display_name":"Qijie Shao","orcid":"https://orcid.org/0009-0000-2145-4077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qijie Shao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062387897","display_name":"Jinghao Yan","orcid":"https://orcid.org/0000-0001-6408-6665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinghao Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700905","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0003-3902-7131"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062644421","display_name":"Xian Shi","orcid":"https://orcid.org/0000-0002-4120-7361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xian Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100703624","display_name":"Pengfei Hu","orcid":"https://orcid.org/0009-0000-4537-6288"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","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":1.3495,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82661205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3719","last_page":"3723"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9876999855041504,"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":0.9864000082015991,"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/stress","display_name":"Stress (linguistics)","score":0.8095157742500305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6662234663963318},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.6604310274124146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6538850665092468},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6401247978210449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49278023838996887},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.48568472266197205},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.47228914499282837},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41369250416755676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4127448797225952},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.39066654443740845},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.15219160914421082}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8095157742500305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662234663963318},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.6604310274124146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6538850665092468},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6401247978210449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49278023838996887},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.48568472266197205},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.47228914499282837},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41369250416755676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4127448797225952},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.39066654443740845},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.15219160914421082},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10444","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10444","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W3031252497","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W162378616"],"abstract_inverted_index":{"General":[0],"accent":[1,22,43,60,72,80,96,115],"recognition":[2],"(AR)":[3],"models":[4],"tend":[5],"to":[6,32,49,89,122],"directly":[7],"extract":[8],"low-level":[9],"information":[10],"from":[11],"spectrums,":[12],"which":[13,151],"always":[14],"significantly":[15],"overfit":[16],"on":[17,158,173],"speakers":[18],"or":[19],"channels.":[20],"Considering":[21],"can":[23,152],"be":[24,38,99],"regarded":[25],"as":[26,45,55,93],"a":[27,118,124,177,182],"series":[28],"of":[29,52,145],"shifts":[30],"relative":[31,179],"native":[33,53],"pronunciation,":[34],"distinguishing":[35],"accents":[36],"will":[37],"an":[39,56,79],"easier":[40],"task":[41],"with":[42,117,129],"shift":[44,61,73,97,116],"input.":[46],"But":[47],"due":[48],"the":[50,59,85,102,105,114,133,186],"lack":[51],"utterance":[54],"anchor,":[57],"estimating":[58],"is":[62,136],"difficult.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,112],"propose":[68],"linguistic-acoustic":[69,125],"similarity":[70],"based":[71],"(LASAS)":[74],"for":[75],"AR":[76,155],"tasks.":[77],"For":[78],"speech":[81],"utterance,":[82],"after":[83],"mapping":[84],"corresponding":[86],"text":[87,120],"vector":[88,121],"multiple":[90],"accent-associated":[91],"spaces":[92],"anchors,":[94],"its":[95],"could":[98],"estimated":[100],"by":[101,141],"similarities":[103],"between":[104],"acoustic":[106,131,149],"embedding":[107],"and":[108,138,148],"those":[109],"anchors.":[110],"Then,":[111],"concatenate":[113],"dimension-reduced":[119],"obtain":[123],"bimodal":[126,134],"representation.":[127],"Compared":[128],"pure":[130],"embedding,":[132],"representation":[135],"richer":[137],"more":[139],"clear":[140],"taking":[142],"full":[143],"advantage":[144],"both":[146],"linguistic":[147],"information,":[150],"effectively":[153],"improve":[154],"performance.":[156],"Experiments":[157],"Accented":[159],"English":[160],"Speech":[161],"Recognition":[162],"Challenge":[163],"(AESRC)":[164],"dataset":[165],"show":[166],"that":[167],"our":[168],"method":[169],"achieves":[170],"77.42%":[171],"accuracy":[172],"Test":[174],"set,":[175],"obtaining":[176],"6.94%":[178],"improvement":[180],"over":[181],"competitive":[183],"system":[184],"in":[185],"challenge.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}