{"id":"https://openalex.org/W2966163367","doi":"https://doi.org/10.1109/taslp.2019.2933325","title":"Advancing Acoustic-to-Word CTC Model With Attention and Mixed-Units","display_name":"Advancing Acoustic-to-Word CTC Model With Attention and Mixed-Units","publication_year":2019,"publication_date":"2019-08-05","ids":{"openalex":"https://openalex.org/W2966163367","doi":"https://doi.org/10.1109/taslp.2019.2933325","mag":"2966163367"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2933325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2933325","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":null,"display_name":"Amit Das","orcid":"https://orcid.org/0000-0002-8823-8026"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Das","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8823-8026","affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578397","display_name":"Guoli Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoli Ye","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":3.8931,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.94561037,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"27","issue":"12","first_page":"1880","last_page":"1892"},"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/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9983000159263611,"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":0.765945553779602},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6871805787086487},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6131591796875},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.581028938293457},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5758591890335083},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.554476797580719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5255312323570251},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4576321244239807},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4464346170425415},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.43208539485931396},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42780566215515137},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31073564291000366},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11195573210716248},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09651646018028259},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08689364790916443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.765945553779602},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6871805787086487},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6131591796875},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.581028938293457},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5758591890335083},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.554476797580719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5255312323570251},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4576321244239807},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4464346170425415},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.43208539485931396},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42780566215515137},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31073564291000366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11195573210716248},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09651646018028259},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08689364790916443},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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},{"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/taslp.2019.2933325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2933325","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W58893626","https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1501139663","https://openalex.org/W1533416326","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W1942035323","https://openalex.org/W2050958850","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2094035326","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2166850712","https://openalex.org/W2194775991","https://openalex.org/W2296073425","https://openalex.org/W2327501763","https://openalex.org/W2515801922","https://openalex.org/W2521999726","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2548332580","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2627092829","https://openalex.org/W2735006420","https://openalex.org/W2746192915","https://openalex.org/W2748163763","https://openalex.org/W2750499125","https://openalex.org/W2772048672","https://openalex.org/W2808939837","https://openalex.org/W2913340405","https://openalex.org/W2936123380","https://openalex.org/W2937148911","https://openalex.org/W2937649809","https://openalex.org/W2939297570","https://openalex.org/W2952288254","https://openalex.org/W2962742956","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962961016","https://openalex.org/W2962962542","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963303028","https://openalex.org/W2963403868","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963523217","https://openalex.org/W2963920996","https://openalex.org/W2963953073","https://openalex.org/W2963970535","https://openalex.org/W2964308564","https://openalex.org/W4385245566","https://openalex.org/W6602415096","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6630005552","https://openalex.org/W6638749077","https://openalex.org/W6640090968","https://openalex.org/W6640708543","https://openalex.org/W6662788660","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6727690538","https://openalex.org/W6728811460","https://openalex.org/W6734588641","https://openalex.org/W6739901393"],"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/W1997182898","https://openalex.org/W2944691285"],"abstract_inverted_index":{"The":[0,168],"acoustic-to-word":[1,220],"model":[2,36,60,71,86,245,250],"based":[3],"on":[4,38,209],"the":[5,27,30,34,39,52,57,63,78,138,150,172,176,197,236],"Connectionist":[6],"Temporal":[7],"Classification":[8],"(CTC)":[9],"criterion":[10],"is":[11,51,87],"a":[12,85,95,110,159,185,191,210,227,257],"natural":[13],"end-to-end":[14],"(E2E)":[15],"system":[16],"directly":[17,136],"targeting":[18],"word":[19,160,177,231,238],"as":[20,81],"output":[21,32],"unit.":[22],"Two":[23],"issues":[24],"exist":[25],"in":[26,89,92,230],"system:":[28],"first,":[29],"current":[31,40],"of":[33,98,112,202],"CTC":[35,59,139,143,156,163,170,174,178,193,239,262],"relies":[37],"input":[41],"and":[42,115,127,144,161,205,224,266],"does":[43],"not":[44],"account":[45],"for":[46],"context":[47],"weighted":[48],"inputs.":[49],"This":[50,67],"hard":[53],"alignment":[54],"issue.":[55,66],"Second,":[56,147],"word-based":[58],"suffers":[61],"from":[62],"out-of-vocabulary":[64],"(OOV)":[65],"means":[68],"it":[69],"can":[70],"only":[72,94],"frequently":[73],"occurring":[74],"words":[75,80,199,204],"while":[76],"tagging":[77],"remaining":[79],"OOV.":[82,181],"Hence,":[83],"such":[84],"limited":[88],"its":[90],"capacity":[91],"recognizing":[93],"fixed":[96],"set":[97],"frequent":[99,203],"words.":[100],"In":[101,117],"this":[102],"study,":[103],"we":[104,119,131,153,183],"propose":[105,184],"addressing":[106],"these":[107],"problems":[108],"using":[109,141,222,247],"combination":[111],"attention":[113,133,223],"mechanism":[114],"mixed-units.":[116],"particular,":[118],"introduce":[120],"Attention":[121,142],"CTC,":[122,124,126],"Self-Attention":[123,145],"Hybrid":[125,155,169],"Mixed-unit":[128,192],"CTC.":[129,146],"First,":[130],"blend":[132],"modeling":[134],"capabilities":[135],"into":[137,200],"network":[140],"to":[148],"alleviate":[149],"OOV":[151,198],"issue,":[152],"present":[154],"which":[157,194],"uses":[158],"letter":[162,173],"with":[164,263],"shared":[165],"hidden":[166],"layers.":[167],"consults":[171],"when":[175],"emits":[179],"an":[180,243],"Then,":[182],"much":[186],"better":[187],"solution":[188,221],"by":[189,240,268],"training":[190],"decomposes":[195],"all":[196],"sequences":[201],"multi-letter":[206],"units.":[207],"Evaluated":[208],"3400":[211],"hours":[212],"Microsoft":[213],"Cortana":[214],"voice":[215],"assistant":[216],"task,":[217],"our":[218],"final":[219],"mixed-units":[225],"achieves":[226],"relative":[228],"reduction":[229],"error":[232],"rate":[233],"(WER)":[234],"over":[235],"vanilla":[237],"12.09%.":[241],"Such":[242],"E2E":[244],"without":[246],"any":[248],"language":[249],"(LM)":[251],"or":[252],"complex":[253],"decoder":[254,267],"also":[255],"outperforms":[256],"traditional":[258],"context-dependent":[259],"(CD)":[260],"phoneme":[261],"strong":[264],"LM":[265],"6.79%":[269],"relative.":[270]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}