{"id":"https://openalex.org/W3114972750","doi":"https://doi.org/10.1109/gcce50665.2020.9292012","title":"Multilingual acoustic model training based on phoneme set conversion","display_name":"Multilingual acoustic model training based on phoneme set conversion","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3114972750","doi":"https://doi.org/10.1109/gcce50665.2020.9292012","mag":"3114972750"},"language":"en","primary_location":{"id":"doi:10.1109/gcce50665.2020.9292012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9292012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","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/A5022767796","display_name":"Yuuki Tachioka","orcid":"https://orcid.org/0009-0002-0587-2943"},"institutions":[{"id":"https://openalex.org/I4210132650","display_name":"Denso (Japan)","ror":"https://ror.org/04hkpfa76","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210132650"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuuki Tachioka","raw_affiliation_strings":["Denso IT Laboratory, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Denso IT Laboratory, Tokyo, Japan","institution_ids":["https://openalex.org/I4210132650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022767796"],"corresponding_institution_ids":["https://openalex.org/I4210132650"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17601375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"104","issue":null,"first_page":"921","last_page":"922"},"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":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8507208824157715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6559531092643738},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6190525889396667},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6124785542488098},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5954024791717529},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5503128170967102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155494213104248},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5110307931900024},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4810888469219208},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28164559602737427},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06524541974067688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507208824157715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6559531092643738},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6190525889396667},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6124785542488098},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5954024791717529},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5503128170967102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155494213104248},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5110307931900024},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4810888469219208},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28164559602737427},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06524541974067688},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce50665.2020.9292012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9292012","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2769437540","https://openalex.org/W2786102402","https://openalex.org/W2786835190","https://openalex.org/W6746041127"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W2126322296","https://openalex.org/W4383605217","https://openalex.org/W2533508831","https://openalex.org/W4287644835","https://openalex.org/W48790062","https://openalex.org/W2742699532","https://openalex.org/W4281389974","https://openalex.org/W3092281475"],"abstract_inverted_index":{"For":[0],"multilingual":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR),":[5],"acoustic":[6],"models":[7],"are":[8,33,54,75],"often":[9],"trained":[10],"on":[11,64],"multiple":[12],"language":[13,20,27,74],"datasets.":[14],"The":[15],"ASR":[16],"of":[17,79,89],"a":[18,58],"target":[19,81],"can":[21],"be":[22],"improved":[23],"by":[24],"using":[25],"auxiliary":[26,73],"data.":[28],"Generally,":[29],"universal":[30],"phoneme":[31,42,52,65],"sets":[32,53],"used":[34],"in":[35,68],"order":[36],"to":[37],"eliminate":[38],"the":[39,72,80,87],"differences":[40],"between":[41],"sets.":[43],"However,":[44],"this":[45],"approach":[46],"is":[47],"inefficient":[48],"for":[49],"languages":[50],"whose":[51],"similar.":[55],"We":[56],"propose":[57],"more":[59],"efficient":[60],"training":[61],"method":[62],"based":[63],"set":[66],"conversion,":[67],"which":[69],"phonemes":[70],"from":[71],"converted":[76],"into":[77],"those":[78],"language.":[82],"In":[83],"addition,":[84],"we":[85],"examined":[86],"construction":[88],"context":[90],"trees.":[91]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}