{"id":"https://openalex.org/W2903484711","doi":"https://doi.org/10.1109/icassp.2019.8682533","title":"Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain","display_name":"Domain Attentive Fusion for End-to-end Dialect Identification with Unknown Target Domain","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2903484711","doi":"https://doi.org/10.1109/icassp.2019.8682533","mag":"2903484711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5020263683","display_name":"Suwon Shon","orcid":null},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suwon Shon","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5951","last_page":"5955"},"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":0.9970999956130981,"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":0.9957000017166138,"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":0.8068506717681885},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7268272042274475},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6915406584739685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6112181544303894},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5604483485221863},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5423529744148254},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5402843952178955},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5173077583312988},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4808517098426819},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4623478651046753},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46205416321754456},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37345755100250244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35378068685531616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07950693368911743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8068506717681885},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7268272042274475},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6915406584739685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6112181544303894},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5604483485221863},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5423529744148254},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5402843952178955},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5173077583312988},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4808517098426819},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4623478651046753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46205416321754456},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37345755100250244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35378068685531616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07950693368911743},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682533","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1999033484","https://openalex.org/W2181594395","https://openalex.org/W2186162535","https://openalex.org/W2360384684","https://openalex.org/W2398046886","https://openalex.org/W2581955877","https://openalex.org/W2620757702","https://openalex.org/W2735780771","https://openalex.org/W2793012778","https://openalex.org/W2805504157","https://openalex.org/W2806839981","https://openalex.org/W2899166839","https://openalex.org/W2916297645","https://openalex.org/W2962679215","https://openalex.org/W2962922562","https://openalex.org/W2962945654","https://openalex.org/W2963134917","https://openalex.org/W2963466763","https://openalex.org/W2963499843","https://openalex.org/W6733346999","https://openalex.org/W6738902873","https://openalex.org/W6755263701","https://openalex.org/W6756465896"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W1583422155","https://openalex.org/W3213252596","https://openalex.org/W1649619740","https://openalex.org/W1534006406"],"abstract_inverted_index":{"End-to-end":[0],"deep":[1],"learning":[2],"language":[3],"or":[4,12],"dialect":[5],"identification":[6,19,148],"systems":[7,29],"operate":[8],"on":[9,107,129,180],"the":[10,36,40,53,78,83,116,122],"spectrogram":[11],"other":[13,130],"acoustic":[14],"feature":[15],"and":[16,162,185],"directly":[17],"generate":[18],"scores":[20],"for":[21,27,145,166],"each":[22],"class.":[23],"An":[24],"important":[25],"issue":[26],"end-to-end":[28,146],"is":[30,59,74,113],"to":[31,45,62,81,85,94,103,114,193],"have":[32,104],"some":[33],"knowledge":[34,120],"of":[35,121,173,183],"application":[37],"domain,":[38],"because":[39],"system":[41,84],"can":[42],"be":[43],"vulnerable":[44],"use":[46,97],"cases":[47],"that":[48,72],"were":[49,178],"not":[50],"seen":[51],"in":[52,77,101],"training":[54,79,99],"phase;":[55],"such":[56],"a":[57,64,98,140,156,167,181],"scenario":[58],"often":[60],"referred":[61],"as":[63,132],"domain":[65,124,141,168,201],"mismatched":[66,169],"condition.":[67,170],"In":[68,88],"general,":[69],"we":[70,91,138,154],"assume":[71],"there":[73],"enough":[75],"variation":[76],"dataset":[80,100,157],"expose":[82],"multiple":[86],"domains.":[87,110],"this":[89,136],"work,":[90],"study":[92],"how":[93],"best":[95],"make":[96],"order":[102],"maximum":[105],"effectiveness":[106],"unknown":[108],"target":[109,123,200],"Our":[111],"goal":[112],"process":[115],"input":[117],"without":[118,197],"any":[119,198],"while":[125],"preserving":[126],"robust":[127],"performance":[128,190],"domains":[131],"well.":[133],"To":[134,150],"accomplish":[135],"objective,":[137],"propose":[139],"attentive":[142],"fusion":[143],"approach":[144],"dialect/language":[147],"systems.":[149],"help":[151],"with":[152],"experimentation,":[153],"collect":[155],"from":[158],"three":[159],"different":[160],"domains,":[161],"create":[163],"experimental":[164],"protocols":[165],"The":[171],"results":[172],"our":[174],"proposed":[175],"approach,":[176],"which":[177],"tested":[179],"variety":[182],"broadcast":[184],"YouTube":[186],"data,":[187],"shows":[188],"significant":[189],"gain":[191],"compared":[192],"traditional":[194],"approaches,":[195],"even":[196],"prior":[199],"information.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}