{"id":"https://openalex.org/W4319862452","doi":"https://doi.org/10.1109/slt54892.2023.10022466","title":"Alternate Intermediate Conditioning with Syllable-Level and Character-Level Targets for Japanese ASR","display_name":"Alternate Intermediate Conditioning with Syllable-Level and Character-Level Targets for Japanese ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862452","doi":"https://doi.org/10.1109/slt54892.2023.10022466"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022466","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022466","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["LINE Corporation,Tokyo,Japan","LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation,Tokyo,Japan","LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["LINE Corporation,Tokyo,Japan","LINE Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LINE Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I4210096607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00732994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"76","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9969000220298767,"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/syllable","display_name":"Syllable","score":0.8040435910224915},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7557179927825928},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7418539524078369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7126104235649109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7036952376365662},{"id":"https://openalex.org/keywords/kanji","display_name":"Kanji","score":0.6856163144111633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5358909368515015},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5279428362846375},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5248246788978577},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4805658161640167},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.33478033542633057},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17659714818000793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14527159929275513},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14436393976211548},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07004490494728088}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.8040435910224915},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7557179927825928},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7418539524078369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126104235649109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7036952376365662},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.6856163144111633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5358909368515015},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5279428362846375},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5248246788978577},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4805658161640167},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.33478033542633057},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17659714818000793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14527159929275513},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14436393976211548},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07004490494728088},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022466","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022466","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2603679025","https://openalex.org/W2785450052","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963250244","https://openalex.org/W2963303028","https://openalex.org/W3010788072","https://openalex.org/W3016010032","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3112157188","https://openalex.org/W3162249256","https://openalex.org/W3169714379","https://openalex.org/W3171851140","https://openalex.org/W3197140813","https://openalex.org/W3205920203","https://openalex.org/W3206573929","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W4372269205","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6753411874","https://openalex.org/W6779469704","https://openalex.org/W6780218876","https://openalex.org/W6784531339","https://openalex.org/W6797382298","https://openalex.org/W6802800485","https://openalex.org/W6838599634"],"related_works":["https://openalex.org/W2149918773","https://openalex.org/W418410444","https://openalex.org/W2250289928","https://openalex.org/W4230639968","https://openalex.org/W2356756483","https://openalex.org/W2368258406","https://openalex.org/W2348863460","https://openalex.org/W1928047647","https://openalex.org/W2320366352","https://openalex.org/W3119090387"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2,7],"recognition":[3],"directly":[4],"maps":[5],"input":[6],"to":[8,49,98],"characters.":[9,35,52],"However,":[10],"the":[11,39,55,73,79,83,116,120],"mapping":[12,46],"can":[13],"be":[14,21],"problematic":[15],"when":[16,27],"several":[17],"different":[18,34],"pronunciations":[19],"should":[20],"mapped":[22],"into":[23],"one":[24,28],"character":[25],"or":[26],"pronunciation":[29],"is":[30],"shared":[31],"among":[32],"many":[33],"Japanese":[36,50,113],"ASR":[37],"suffers":[38],"most":[40],"from":[41,82],"such":[42],"many-to-one":[43],"and":[44,63,91,105,123],"one-to-many":[45],"problems":[47],"due":[48],"kanji":[51],"To":[53],"alleviate":[54],"problems,":[56],"we":[57],"introduce":[58],"explicit":[59],"interaction":[60],"between":[61,103],"characters":[62,104],"syllables":[64],"using":[65],"Self-conditioned":[66,124],"connectionist":[67],"temporal":[68],"classification":[69],"(CTC),":[70],"in":[71],"which":[72],"upper":[74],"layers":[75],"are":[76],"\u201cself-conditioned\u201d":[77],"on":[78,109],"intermediate":[80,93],"predictions":[81,94],"lower":[84],"layers.":[85],"The":[86],"proposed":[87,117],"method":[88,118],"utilizes":[89],"character-level":[90],"syllable-level":[92],"as":[95],"conditioning":[96],"features":[97],"deal":[99],"with":[100],"mutual":[101],"dependency":[102],"syllables.":[106],"Experimental":[107],"results":[108],"Corpus":[110],"of":[111],"Spontaneous":[112],"show":[114],"that":[115],"outperformed":[119],"conventional":[121],"multi-task":[122],"CTC":[125],"methods.":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-02-11T00:00:00"}