{"id":"https://openalex.org/W2044577954","doi":"https://doi.org/10.1109/icassp.2013.6639092","title":"Automatic localization of a language-independent sub-network on deep neural networks trained by multi-lingual speech","display_name":"Automatic localization of a language-independent sub-network on deep neural networks trained by multi-lingual speech","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2044577954","doi":"https://doi.org/10.1109/icassp.2013.6639092","mag":"2044577954"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5077037266","display_name":"Shigeki Matsuda","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shigeki Matsuda","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Commun. Lab., Nat. Inst. of Inf. & Commun. Technol., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Commun. Lab., Nat. Inst. of Inf. & Commun. Technol., Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Commun. Lab., Nat. Inst. of Inf. & Commun. Technol., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Commun. Lab., Nat. Inst. of Inf. & Commun. Technol., Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108760549","display_name":"Hideki Kashioka","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Kashioka","raw_affiliation_strings":["Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","Spoken Language Commun. Lab., Nat. Inst. of Inf. & Commun. Technol., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Spoken Language Communication Laboratory, National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Spoken Language Commun. Lab., Nat. Inst. of Inf. & Commun. Technol., Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077037266"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.4944,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76435743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"7359","last_page":"7362"},"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":0.9991999864578247,"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":0.9986000061035156,"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":0.8550708293914795},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6450958847999573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6431780457496643},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.6245923042297363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5650746822357178},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5443347096443176},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5203853845596313},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.48064056038856506},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47998806834220886},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4423624277114868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8550708293914795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6450958847999573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6431780457496643},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.6245923042297363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5650746822357178},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5443347096443176},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5203853845596313},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.48064056038856506},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47998806834220886},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4423624277114868},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1010.3761","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1010.3761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Xugang_Lu/publication/261126053_Automatic_localization_of_a_language-independent_sub-network_on_deep_neural_networks_trained_by_multi-lingual_speech/links/547818fb0cf293e2da283d2a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W196761320","https://openalex.org/W1498436455","https://openalex.org/W1604771987","https://openalex.org/W1993882792","https://openalex.org/W2072128103","https://openalex.org/W2116064496","https://openalex.org/W2120209245","https://openalex.org/W2125234026","https://openalex.org/W2127982613","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W4231109964","https://openalex.org/W4285719527","https://openalex.org/W6608133726","https://openalex.org/W6635896687"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3147584709","https://openalex.org/W2977677679","https://openalex.org/W1992327129","https://openalex.org/W2381986121","https://openalex.org/W2370918718","https://openalex.org/W2256933480","https://openalex.org/W2027854990","https://openalex.org/W2370081953","https://openalex.org/W2888189389"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"been":[5],"successfully":[6],"applied":[7],"to":[8,51,86,100,112],"automatic":[9],"speech":[10,62,74,123,165],"recognition":[11],"(ASR).":[12],"However,":[13],"no":[14],"study":[15],"has":[16],"investigated":[17],"the":[18,27,41,87,101],"possibility":[19],"of":[20,32,40,167],"building":[21],"a":[22,37,48,53,71,110,118,149,161],"language-independent":[23,56,76,150],"sub-network":[24,151],"DNN":[25,54,72,119,152],"as":[26,160],"basis":[28],"for":[29,73,164],"further":[30],"training":[31,63],"any":[33],"new":[34,169],"language":[35],"using":[36,60],"simple":[38],"plug-in":[39],"sub-network.":[42],"In":[43],"this":[44,106],"paper,":[45],"we":[46,108],"propose":[47,109],"novel":[49],"technique":[50,111,140,156],"split":[52],"into":[55],"and":[57,127],"-dependent":[58],"sub-networks":[59,116,133],"multi-lingual":[61,122],"data.":[64,124],"Our":[65],"basic":[66],"assumption":[67],"is":[68,79,93],"that,":[69],"in":[70,81,95,117,131,141],"processing,":[75],"feature":[77],"processing":[78,92,129,166],"done":[80],"stages":[82,96],"that":[83,97,148],"are":[84,98,134],"near":[85,99],"input":[88],"layer,":[89],"while":[90],"language-dependent":[91,126],"performed":[94],"output":[102],"layer.":[103],"Based":[104],"on":[105],"assumption,":[107],"simultaneously":[113],"optimize":[114],"multiple":[115],"trained":[120],"with":[121],"The":[125,145],"-independent":[128],"boundaries":[130],"individual":[132],"segmented":[135],"automatically.":[136],"We":[137],"test":[138],"our":[139,155],"phoneme":[142],"classification":[143],"experiments.":[144],"results":[146],"demonstrate":[147],"extracted":[153],"by":[154],"can":[157],"be":[158],"used":[159],"universal":[162],"network":[163],"additional":[168],"languages.":[170]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}