{"id":"https://openalex.org/W2922309491","doi":"https://doi.org/10.23919/apsipa.2018.8659784","title":"Relevant Phonetic-aware Neural Acoustic Models using Native English and Japanese Speech for Japanese-English Automatic Speech Recognition","display_name":"Relevant Phonetic-aware Neural Acoustic Models using Native English and Japanese Speech for Japanese-English Automatic Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922309491","doi":"https://doi.org/10.23919/apsipa.2018.8659784","mag":"2922309491"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659784","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"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":true,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048165130","display_name":"Suguru Kabashima","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Suguru Kabashima","raw_affiliation_strings":["The University of Tokyo, japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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 Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024724493","display_name":"Satoshi Kobashikawa","orcid":null},"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":"Satoshi Kobashikawa","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067744302","display_name":"Yoshikazu Yamaguchi","orcid":null},"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":"Yoshikazu Yamaguchi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067237053","display_name":"Yushi Aono","orcid":null},"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":"Yushi Aono","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060644399"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19315943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1435","last_page":"1439"},"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":0.9977999925613403,"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":0.7624422311782837},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7143939733505249},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7074244022369385},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5810133814811707},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4946736991405487},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.42418372631073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40724316239356995},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3959267735481262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3676253855228424},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3136213421821594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7624422311782837},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7143939733505249},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7074244022369385},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5810133814811707},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4946736991405487},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42418372631073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40724316239356995},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3959267735481262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3676253855228424},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3136213421821594},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659784","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659784","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"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":25,"referenced_works":["https://openalex.org/W143647774","https://openalex.org/W1499999342","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2015633636","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2094147890","https://openalex.org/W2101066392","https://openalex.org/W2138889249","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2169883442","https://openalex.org/W2294108103","https://openalex.org/W2403004229","https://openalex.org/W2403766732","https://openalex.org/W2406753715","https://openalex.org/W2633221078","https://openalex.org/W2665095164","https://openalex.org/W2699195338","https://openalex.org/W6605885551","https://openalex.org/W6696757691","https://openalex.org/W6713298849","https://openalex.org/W6713877832","https://openalex.org/W6739324457"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W1909292483","https://openalex.org/W2105439218"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"relevant":[3,161,187],"phonetic-aware":[4,162,188],"neural":[5,163,180,189],"acoustic":[6,36,76,122,164,181,190],"models":[7,37,191],"that":[8,40,51,63,128,222],"leverage":[9,84],"native":[10,14,56,89,92,104,107,130,145,175,178,202,209],"Japanese":[11,93,146,179,203],"speech":[12,16,21,33,45,48,73,94,132,147],"and":[13,91,106,177,205],"English":[15,57,90,105,131,176,210],"to":[17,29,43,67,82,112,116],"create":[18],"improved":[19],"automatic":[20],"recognition":[22],"(ASR)":[23],"of":[24,55,71,88,120,140,155,174,196,201,208,215,226],"Japanese-English":[25,32,44,47,72,98,121,197],"speech.":[26,58,211],"In":[27,158],"order":[28],"accurately":[30],"transcribe":[31],"in":[34,135,150],"ASR,":[35],"are":[38,41],"needed":[39],"specific":[42],"since":[46,97],"exhibits":[49],"pronunciations":[50],"differ":[52],"from":[53],"those":[54],"The":[59],"major":[60],"problem":[61],"is":[62,65,81,99,111,133,148,168],"it":[64],"difficult":[66],"collect":[68],"a":[69],"lot":[70],"for":[74],"constructing":[75],"models.":[77,123,182],"Therefore,":[78],"our":[79,216],"motivation":[80],"efficiently":[83],"the":[85,118,129,137,144,152,159,186],"significant":[86],"amounts":[87],"material":[95],"available":[96],"definitely":[100],"affected":[101],"by":[102,170,192],"both":[103],"Japanese.":[108],"Our":[109,183],"idea":[110,167],"utilize":[113],"them":[114],"indirectly":[115],"enhance":[117],"phonetic-awareness":[119],"It":[124],"can":[125],"be":[126],"expected":[127],"effective":[134,149],"enhancing":[136,151],"classification":[138,153],"performance":[139,154],"English-like":[141],"phonemes,":[142],"while":[143],"Japanese-like":[156],"phonemes.":[157],"proposed":[160],"models,":[165],"this":[166],"implemented":[169],"utilizing":[171,193],"bottleneck":[172],"features":[173],"experiments":[184],"construct":[185],"300":[194],"hours":[195,200,207],"speech,":[198,204],"1,500":[199],"900":[206],"We":[212],"demonstrate":[213],"effectiveness":[214],"proposal":[217],"using":[218],"evaluation":[219],"data":[220],"sets":[221],"involve":[223],"four":[224],"levels":[225],"Japanese-English.":[227]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}