{"id":"https://openalex.org/W2826003142","doi":"https://doi.org/10.1109/icassp.2018.8461648","title":"Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning","display_name":"Speaker Invariant Feature Extraction for Zero-Resource Languages with Adversarial Learning","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2826003142","doi":"https://doi.org/10.1109/icassp.2018.8461648","mag":"2826003142"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5086130681","display_name":"Taira Tsuchiya","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taira Tsuchiya","raw_affiliation_strings":["Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073111123","display_name":"Naohiro Tawara","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":["Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046269496","display_name":"Testuji Ogawa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Testuji Ogawa","raw_affiliation_strings":["Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086130681"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":3.3806,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93890525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2381","last_page":"2385"},"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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":0.9922999739646912,"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":0.783141016960144},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6797147989273071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5978865027427673},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5630910396575928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5529668927192688},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4988138675689697},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46812665462493896},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4650861620903015},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.46489351987838745},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4526228904724121},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43291449546813965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41588589549064636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.783141016960144},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6797147989273071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5978865027427673},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5630910396575928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529668927192688},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4988138675689697},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46812665462493896},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4650861620903015},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.46489351987838745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4526228904724121},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43291449546813965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41588589549064636},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W66167291","https://openalex.org/W128628490","https://openalex.org/W1731081199","https://openalex.org/W1796128977","https://openalex.org/W1836465849","https://openalex.org/W1904365287","https://openalex.org/W1945616565","https://openalex.org/W2002342963","https://openalex.org/W2043878967","https://openalex.org/W2064675550","https://openalex.org/W2078169166","https://openalex.org/W2100768664","https://openalex.org/W2119187236","https://openalex.org/W2126203737","https://openalex.org/W2150769028","https://openalex.org/W2185814970","https://openalex.org/W2395899413","https://openalex.org/W2396043527","https://openalex.org/W2399576818","https://openalex.org/W2404799143","https://openalex.org/W2509930204","https://openalex.org/W2510867321","https://openalex.org/W2730658205","https://openalex.org/W2949117887","https://openalex.org/W2963207607","https://openalex.org/W3028642772","https://openalex.org/W6602705600","https://openalex.org/W6605273041","https://openalex.org/W6637618735","https://openalex.org/W6638159135","https://openalex.org/W6638667902","https://openalex.org/W6640036494","https://openalex.org/W6640425456","https://openalex.org/W6661255737","https://openalex.org/W6675022971","https://openalex.org/W6686687092","https://openalex.org/W6712202099","https://openalex.org/W6712444837","https://openalex.org/W6712553779","https://openalex.org/W6725564769","https://openalex.org/W6777926273"],"related_works":["https://openalex.org/W3013299381","https://openalex.org/W3148366653","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W1560125148","https://openalex.org/W4309346246"],"abstract_inverted_index":{"We":[0,134],"introduce":[1,61,73],"a":[2,10,25,30,62,68,74,78,88,106,121],"novel":[3],"type":[4],"of":[5,52,90],"representation":[6,123],"learning":[7,76],"to":[8,23,77,82,87,113,116,124,131],"obtain":[9],"speaker":[11,36,101],"invariant":[12,86],"feature":[13,64,85,107],"for":[14],"zero-resource":[15,31],"languages.":[16],"Speaker":[17],"adaptation":[18,37],"is":[19,56,129],"an":[20,110],"important":[21],"technique":[22],"build":[24],"robust":[26],"acoustic":[27,50],"model.":[28],"For":[29],"language,":[32],"however,":[33],"conventional":[34],"model-dependent":[35],"methods":[38],"such":[39],"as":[40],"constrained":[41],"maximum":[42],"likelihood":[43],"linear":[44],"regression":[45],"are":[46],"insufficient":[47],"because":[48],"the":[49,53,157],"model":[51],"target":[54],"language":[55],"not":[57],"accessible.":[58],"Therefore,":[59],"we":[60,72],"model-independent":[63],"extraction":[65],"based":[66],"on":[67],"neural":[69],"network.":[70],"Specifically,":[71],"multi-task":[75,150],"bottleneck":[79,84],"feature-based":[80],"approach":[81],"make":[83],"change":[89],"speakers.":[91,133,160],"The":[92],"proposed":[93],"network":[94,104,151],"simultaneously":[95],"tackles":[96],"two":[97],"tasks:":[98],"phoneme":[99],"and":[100],"classifications.":[102],"This":[103],"trains":[105],"extractor":[108],"in":[109,139,159],"adversarial":[111],"manner":[112],"allow":[114],"it":[115,128],"map":[117],"input":[118],"data":[119],"into":[120],"discriminative":[122,154],"predict":[125,132],"phonemes,":[126],"whereas":[127],"difficult":[130],"conduct":[135],"phone":[136],"discriminant":[137],"experiments":[138],"Zero":[140],"Resource":[141],"Speech":[142],"Challenge":[143],"2017.":[144],"Experimental":[145],"results":[146],"showed":[147],"that":[148],"our":[149],"yielded":[152],"more":[153],"features":[155],"eliminating":[156],"variety":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}