{"id":"https://openalex.org/W3205920203","doi":"https://doi.org/10.1109/icassp43922.2022.9746580","title":"Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units","display_name":"Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Units","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205920203","doi":"https://doi.org/10.1109/icassp43922.2022.9746580","mag":"3205920203"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746580","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084333052","display_name":"Keita Karube","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keita Karube","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Department of Communications and Computer Engineering, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102017467"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":1.8698,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87335704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7797","last_page":"7801"},"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":0.9994000196456909,"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":0.9979000091552734,"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":0.760868489742279},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6719844937324524},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6626749038696289},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6560831069946289},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6217021942138672},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6168188452720642},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6046171188354492},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5544688105583191},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5277835726737976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.505003035068512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.491496205329895},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4707161784172058},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.44504451751708984},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.42752254009246826},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2598890960216522},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1497741937637329}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760868489742279},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6719844937324524},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6626749038696289},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6560831069946289},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6217021942138672},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6168188452720642},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6046171188354492},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5544688105583191},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5277835726737976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.505003035068512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491496205329895},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4707161784172058},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.44504451751708984},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.42752254009246826},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2598890960216522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1497741937637329},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746580","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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","score":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338246","display_name":"ACT-X","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1526990717","https://openalex.org/W1828163288","https://openalex.org/W1849277567","https://openalex.org/W1990005915","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2603679025","https://openalex.org/W2607361225","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2889030467","https://openalex.org/W2892009249","https://openalex.org/W2899879954","https://openalex.org/W2902348614","https://openalex.org/W2936774411","https://openalex.org/W2943845043","https://openalex.org/W2944255943","https://openalex.org/W2962739339","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963303028","https://openalex.org/W2963403868","https://openalex.org/W2963483399","https://openalex.org/W2963979492","https://openalex.org/W2964308564","https://openalex.org/W2972430050","https://openalex.org/W2972818416","https://openalex.org/W3015960524","https://openalex.org/W3093579165","https://openalex.org/W3097777922","https://openalex.org/W3097882114","https://openalex.org/W3103005696","https://openalex.org/W3141854550","https://openalex.org/W3147414526","https://openalex.org/W3160987270","https://openalex.org/W3162249256","https://openalex.org/W3169714379","https://openalex.org/W3197140813","https://openalex.org/W3197148831","https://openalex.org/W3198455051","https://openalex.org/W3206573929","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6639204139","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6691770337","https://openalex.org/W6728910023","https://openalex.org/W6739901393","https://openalex.org/W6746299031","https://openalex.org/W6752958021","https://openalex.org/W6754299077","https://openalex.org/W6756987921","https://openalex.org/W6768009688","https://openalex.org/W6784614252","https://openalex.org/W6792376965"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W4205820553","https://openalex.org/W2251441308"],"abstract_inverted_index":{"In":[0,43],"end-to-end":[1,53],"automatic":[2],"speech":[3],"recognition":[4],"(ASR),":[5],"a":[6,17,37,57,137,156],"model":[7,38,60,70,128,153,159],"is":[8,62,71,90],"expected":[9],"to":[10,39,46,78,98,129,172],"implicitly":[11],"learn":[12,40,130],"representations":[13,133],"suitable":[14],"for":[15,36],"recognizing":[16],"word-level":[18,49,100,132],"sequence.":[19],"However,":[20],"the":[21,41,48,82,94,99,113,121,126,131,151,170,174,177],"huge":[22],"abstraction":[23],"gap":[24],"between":[25],"input":[26],"acoustic":[27],"signals":[28],"and":[29,147,160],"output":[30],"linguistic":[31,140],"tokens":[32],"makes":[33],"it":[34],"challenging":[35],"representations.":[42],"this":[44],"work,":[45],"promote":[47],"representation":[50,179],"learning":[51,180],"in":[52],"ASR,":[54],"we":[55,103,124],"propose":[56],"hierarchical":[58],"conditional":[59],"that":[61,150],"based":[63],"on":[64,112,144],"connectionist":[65],"temporal":[66],"classification":[67],"(CTC).":[68],"Our":[69],"trained":[72],"by":[73,135],"auxiliary":[74],"CTC":[75],"losses":[76],"applied":[77],"intermediate":[79],"layers,":[80],"where":[81],"vocabulary":[83],"size":[84],"of":[85,107,139,176],"each":[86,105],"target":[87],"subword":[88],"sequence":[89,108],"gradually":[91],"increased":[92],"as":[93],"layer":[95],"becomes":[96],"close":[97],"output.":[101],"Here,":[102],"make":[104],"level":[106],"prediction":[109],"explicitly":[110],"conditioned":[111],"previous":[114],"sequences":[115],"predicted":[116],"at":[117],"lower":[118],"levels.":[119],"With":[120],"proposed":[122,127,152],"approach,":[123],"expect":[125],"effectively":[134],"exploiting":[136],"hierarchy":[138],"structures.":[141],"Experimental":[142],"results":[143,171],"LibriSpeech-{100h,":[145],"960h}":[146],"TEDLIUM2":[148],"demonstrate":[149],"improves":[154],"over":[155],"standard":[157],"CTCbased":[158],"other":[161],"competitive":[162],"models":[163],"from":[164],"prior":[165],"work.":[166],"We":[167],"further":[168],"analyze":[169],"confirm":[173],"effectiveness":[175],"intended":[178],"with":[181],"our":[182],"model.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}