{"id":"https://openalex.org/W3007302090","doi":"https://doi.org/10.1109/asru46091.2019.9003872","title":"Native Language Identification from Raw Waveforms Using Deep Convolutional Neural Networks with Attentive Pooling","display_name":"Native Language Identification from Raw Waveforms Using Deep Convolutional Neural Networks with Attentive Pooling","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007302090","doi":"https://doi.org/10.1109/asru46091.2019.9003872","mag":"3007302090"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003872","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5030738204","display_name":"Rutuja Ubale","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rutuja Ubale","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068455745","display_name":"Vikram Ramanarayanan","orcid":"https://orcid.org/0000-0001-7810-2769"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikram Ramanarayanan","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030816616","display_name":"Keelan Evanini","orcid":"https://orcid.org/0000-0003-4243-3376"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keelan Evanini","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112228635","display_name":"Chee Wee Leong","orcid":null},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chee Wee Leong","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035943104","display_name":"Chongmin Lee","orcid":"https://orcid.org/0000-0003-4580-6748"},"institutions":[{"id":"https://openalex.org/I1341030882","display_name":"Educational Testing Service","ror":"https://ror.org/03b5q4637","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1341030882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Min Lee","raw_affiliation_strings":["Educational Testing Service Research, USA"],"affiliations":[{"raw_affiliation_string":"Educational Testing Service Research, USA","institution_ids":["https://openalex.org/I1341030882"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030738204"],"corresponding_institution_ids":["https://openalex.org/I1341030882"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60269872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"403","last_page":"410"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9984999895095825,"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":0.8366544246673584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6707780361175537},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6690764427185059},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6646127700805664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6245328187942505},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5991700291633606},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5938328504562378},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5409454107284546},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5121631622314453},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4899224638938904},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.473786324262619},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.471996545791626},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4618714153766632},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4100688397884369},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2909529209136963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366544246673584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6707780361175537},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6690764427185059},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6646127700805664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6245328187942505},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5991700291633606},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5938328504562378},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5409454107284546},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5121631622314453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4899224638938904},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.473786324262619},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.471996545791626},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4618714153766632},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4100688397884369},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2909529209136963},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003872","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003872","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W153989523","https://openalex.org/W331796780","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1600744878","https://openalex.org/W1836465849","https://openalex.org/W1969851134","https://openalex.org/W2108563286","https://openalex.org/W2114925438","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2398826216","https://openalex.org/W2408093180","https://openalex.org/W2508694887","https://openalex.org/W2513006551","https://openalex.org/W2513366685","https://openalex.org/W2513507089","https://openalex.org/W2513797604","https://openalex.org/W2515121265","https://openalex.org/W2516947558","https://openalex.org/W2529337537","https://openalex.org/W2530876040","https://openalex.org/W2584329820","https://openalex.org/W2786839803","https://openalex.org/W2794506738","https://openalex.org/W2806051338","https://openalex.org/W2807627734","https://openalex.org/W2884250895","https://openalex.org/W2886300652","https://openalex.org/W2889351461","https://openalex.org/W2889462515","https://openalex.org/W2890964092","https://openalex.org/W2914465356","https://openalex.org/W2944440087","https://openalex.org/W2962893195","https://openalex.org/W2962901777","https://openalex.org/W2963288440","https://openalex.org/W2964052309","https://openalex.org/W2964121744","https://openalex.org/W2969945254","https://openalex.org/W3104696513","https://openalex.org/W6606199742","https://openalex.org/W6611429183","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6638667902","https://openalex.org/W6712560600","https://openalex.org/W6713548365","https://openalex.org/W6766816269"],"related_works":["https://openalex.org/W2406522397","https://openalex.org/W2970216048","https://openalex.org/W2285052147","https://openalex.org/W2043075591","https://openalex.org/W2725397116","https://openalex.org/W2189089965","https://openalex.org/W2806866760","https://openalex.org/W2798765714","https://openalex.org/W4386021872","https://openalex.org/W1646426535"],"abstract_inverted_index":{"Automatic":[0],"detection":[1],"of":[2,24,91,114,124],"an":[3],"individual's":[4],"native":[5,47,89],"language":[6,15,40,48,90],"(L1)":[7],"based":[8],"on":[9,55,111,150],"speech":[10,25,30],"data":[11],"from":[12,50,95,133],"their":[13],"second":[14],"(L2)":[16],"can":[17],"be":[18],"useful":[19],"for":[20,46],"informing":[21],"a":[22,76,112],"variety":[23],"applications":[26],"such":[27,64],"as":[28,65],"automatic":[29],"recognition":[31],"(ASR),":[32],"speaker":[33,93],"recognition,":[34],"voice":[35],"biometrics,":[36],"and":[37],"computer":[38],"assisted":[39],"learning":[41],"(CALL).":[42],"Previously":[43],"proposed":[44,126,143],"systems":[45],"identification":[49],"L2":[51],"acoustic":[52],"signals":[53],"rely":[54],"traditional":[56],"feature":[57,102],"extraction":[58,103],"pipelines":[59],"to":[60,86,148,156],"extract":[61,130],"relevant":[62],"features":[63,132,154],"mel-filterbanks,":[66],"cepstral":[67],"coefficients,":[68],"i-vectors,":[69],"etc.":[70],"In":[71],"this":[72,109],"paper,":[73],"we":[74],"present":[75],"fully":[77],"convolutional":[78,122],"neural":[79],"network":[80,144],"approach":[81,110],"that":[82,119],"is":[83],"trained":[84],"end-to-end":[85,128],"predict":[87],"the":[88,92,96,101,120,137,151,159],"directly":[94],"raw":[97,134],"waveforms,":[98],"thereby":[99],"removing":[100],"step":[104],"altogether.":[105],"Experimental":[106],"results":[107],"using":[108],"database":[113],"11":[115],"different":[116],"L1s":[117],"suggest":[118],"learnable":[121],"layers":[123],"our":[125,142,146],"attention-based":[127],"model":[129,147],"meaningful":[131],"waveforms.":[135],"Further,":[136],"attentive":[138],"pooling":[139],"mechanism":[140],"in":[141],"enables":[145],"focus":[149],"most":[152],"discriminative":[153],"leading":[155],"improvements":[157],"over":[158],"conventional":[160],"baseline.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}