{"id":"https://openalex.org/W4375869301","doi":"https://doi.org/10.1109/icassp49357.2023.10096318","title":"Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models","display_name":"Exploration of Language Dependency for Japanese Self-Supervised Speech Representation Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869301","doi":"https://doi.org/10.1109/icassp49357.2023.10096318"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096318","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104231303","display_name":"Kohei Matsuura","orcid":"https://orcid.org/0009-0000-0884-2200"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007415728","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-8884-9089"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.9897000193595886,"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":0.8289612531661987},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6073227524757385},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.602887749671936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5272002816200256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49471160769462585},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4886675179004669},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44930440187454224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8289612531661987},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6073227524757385},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.602887749671936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5272002816200256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49471160769462585},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4886675179004669},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44930440187454224},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096318","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2005522781","https://openalex.org/W2127141656","https://openalex.org/W2251321385","https://openalex.org/W2765486990","https://openalex.org/W2842511635","https://openalex.org/W2933138175","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2995181338","https://openalex.org/W3016181583","https://openalex.org/W3030437843","https://openalex.org/W3034729383","https://openalex.org/W3036601975","https://openalex.org/W3093579165","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3102342027","https://openalex.org/W3161669994","https://openalex.org/W3196419581","https://openalex.org/W3197202691","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3198446739","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4221145109","https://openalex.org/W4221151577","https://openalex.org/W4226033575","https://openalex.org/W4226074601","https://openalex.org/W4281492411","https://openalex.org/W4297808394","https://openalex.org/W4297841520","https://openalex.org/W4297841844","https://openalex.org/W6691770337","https://openalex.org/W6745289305","https://openalex.org/W6771467084","https://openalex.org/W6779469704","https://openalex.org/W6780218876","https://openalex.org/W6784614252","https://openalex.org/W6810007534"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W2154771632","https://openalex.org/W4211085505","https://openalex.org/W3122478268","https://openalex.org/W2084758217","https://openalex.org/W408804804","https://openalex.org/W4231021675","https://openalex.org/W3086365953","https://openalex.org/W4226072953","https://openalex.org/W2392606101"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1],"(SSL)":[2],"has":[3,28],"been":[4,22,29],"dramatically":[5],"successful":[6],"not":[7],"only":[8],"in":[9,13,25,40,97,129],"monolingual":[10,44,73],"but":[11],"also":[12],"cross-lingual":[14,37,71,107],"settings.":[15],"However,":[16],"since":[17],"the":[18,67,82,125],"two":[19,76],"settings":[20],"have":[21],"studied":[23],"individually":[24],"general,":[26],"there":[27,140],"little":[30],"research":[31],"focusing":[32],"on":[33,135],"how":[34,92],"effective":[35],"a":[36,43,106],"model":[38,108],"is":[39,99,141],"comparison":[41],"with":[42,55,110],"model.":[45],"In":[46],"this":[47,51,150],"paper,":[48],"we":[49,63,90,122,148],"investigate":[50,124],"fundamental":[52],"question":[53],"empirically":[54],"Japanese":[56,98,130,154],"automatic":[57],"speech":[58],"recognition":[59],"(ASR)":[60],"tasks.":[61,138],"First,":[62],"begin":[64],"by":[65],"comparing":[66],"ASR":[68,137],"performance":[69,103,134],"of":[70,112,114,116,127],"and":[72,131],"models":[74],"for":[75,146],"different":[77],"language":[78],"tasks":[79],"while":[80],"keeping":[81],"acoustic":[83],"domain":[84],"as":[85,87],"identical":[86],"possible.":[88],"Then,":[89],"examine":[91],"much":[93],"unlabeled":[94],"data":[95],"collected":[96],"needed":[100],"to":[101,105],"achieve":[102],"comparable":[104],"pre-trained":[109],"tens":[111],"thousands":[113],"hours":[115],"English":[117],"and/or":[118],"multilingual":[119],"data.":[120],"Finally,":[121],"extensively":[123],"effectiveness":[126],"SSL":[128,144,155],"demonstrate":[132],"state-of-the-art":[133],"multiple":[136],"Since":[139],"no":[142],"comprehensive":[143],"study":[145,151],"Japanese,":[147],"hope":[149],"will":[152],"guide":[153],"research.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
