{"id":"https://openalex.org/W2963970535","doi":"https://doi.org/10.1109/icassp.2018.8462017","title":"Advancing Acoustic-to-Word CTC Model","display_name":"Advancing Acoustic-to-Word CTC Model","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963970535","doi":"https://doi.org/10.1109/icassp.2018.8462017","mag":"2963970535"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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 AI and Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","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 AI and Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101814582","display_name":"Amit Das","orcid":"https://orcid.org/0000-0001-7733-2976"},"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 AI and Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","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 AI and Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","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 AI and Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","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":null,"apc_paid":null,"fwci":7.7848,"has_fulltext":false,"cited_by_count":89,"citation_normalized_percentile":{"value":0.97870791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5794","last_page":"5798"},"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9984999895095825,"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":0.8007825613021851},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6925857067108154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6330304145812988},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5988476872444153},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5974532961845398},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5783081650733948},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5269808769226074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5241466164588928},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5016567707061768},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4507567286491394},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.44534459710121155},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4214906692504883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39923784136772156},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2594447135925293},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08342227339744568},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08121022582054138}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007825613021851},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6925857067108154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6330304145812988},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5988476872444153},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5974532961845398},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5783081650733948},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5269808769226074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5241466164588928},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5016567707061768},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4507567286491394},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.44534459710121155},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4214906692504883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39923784136772156},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2594447135925293},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08342227339744568},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08121022582054138},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462017","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462017","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W58893626","https://openalex.org/W1489125746","https://openalex.org/W1501139663","https://openalex.org/W1533416326","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W2050958850","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2121879602","https://openalex.org/W2143612262","https://openalex.org/W2166850712","https://openalex.org/W2293634267","https://openalex.org/W2515801922","https://openalex.org/W2521999726","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2735006420","https://openalex.org/W2746192915","https://openalex.org/W2748163763","https://openalex.org/W2952288254","https://openalex.org/W2962824709","https://openalex.org/W2962962542","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963523217","https://openalex.org/W2963953073","https://openalex.org/W6602415096","https://openalex.org/W6629052376","https://openalex.org/W6639156005","https://openalex.org/W6640090968","https://openalex.org/W6662788660","https://openalex.org/W6675365184","https://openalex.org/W6684421916","https://openalex.org/W6696934422","https://openalex.org/W6727193155","https://openalex.org/W6746299031","https://openalex.org/W6746497681","https://openalex.org/W6746892368","https://openalex.org/W6747398299","https://openalex.org/W6749566584","https://openalex.org/W6751020722","https://openalex.org/W7027429494"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W1566315437","https://openalex.org/W2594897229","https://openalex.org/W4221142855","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2944691285"],"abstract_inverted_index":{"The":[0],"acoustic-to-word":[1,84,146],"model":[2,18,29,40,65,85,90,100,119,171,176],"based":[3],"on":[4,135],"the":[5,26,32,46,52,69,74,83,97,123,144,149,182],"connectionist":[6],"temporal":[7],"classification":[8],"(CTC)":[9],"criterion":[10],"was":[11],"shown":[12],"as":[13,22,36],"a":[14,62,87,93,110,116,136],"natural":[15],"end-to-end":[16],"(E2E)":[17],"directly":[19],"targeting":[20],"words":[21,44,54,71,125,130],"output":[23,47,58,76],"units.":[24,133],"However,":[25],"word-based":[27,63,98,151],"CTC":[28,64,89,95,99,118,152,186],"suffers":[30],"from":[31],"out-of-vocabulary":[33],"(OOV)":[34],"issue":[35],"it":[37],"can":[38,66],"only":[39,67],"limited":[41],"number":[42],"of":[43,128],"in":[45],"layer":[48],"and":[49,131,191],"maps":[50],"all":[51,122],"remaining":[53],"into":[55,126],"an":[56,169],"OOV":[57,102,124],"node.":[59],"Hence,":[60],"such":[61],"recognize":[68],"frequent":[70,129],"modeled":[72],"by":[73,114,153,193],"network":[75],"nodes.":[77],"Our":[78],"first":[79],"attempt":[80],"to":[81],"improve":[82],"is":[86],"hybrid":[88],"which":[91,120,187],"consults":[92],"letter-based":[94],"when":[96,161],"emits":[101],"tokens":[103],"during":[104],"testing":[105],"time.":[106],"Then,":[107],"we":[108],"propose":[109],"much":[111],"better":[112],"solution":[113,147],"training":[115],"mixed-unit":[117],"decomposes":[121],"sequences":[127],"multi-letter":[132],"Evaluated":[134],"3400":[137],"hours":[138],"Microsoft":[139],"Cortana":[140],"voice":[141],"assistant":[142],"task,":[143],"final":[145],"improves":[148],"baseline":[150],"relative":[154,194],"12.09%":[155],"word":[156],"error":[157],"rate":[158],"(WER)":[159],"reduction":[160],"combined":[162],"with":[163],"our":[164],"proposed":[165],"attention":[166],"CTC.":[167],"Such":[168],"E2E":[170],"without":[172],"using":[173],"any":[174],"language":[175],"(LM)":[177],"or":[178],"complex":[179],"decoder":[180,192],"outperforms":[181],"traditional":[183],"context-dependent":[184],"phoneme":[185],"has":[188],"strong":[189],"LM":[190],"6.79%.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":11}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}