{"id":"https://openalex.org/W2962962542","doi":"https://doi.org/10.1109/icassp.2018.8461558","title":"Advancing Connectionist Temporal Classification with Attention Modeling","display_name":"Advancing Connectionist Temporal Classification with Attention Modeling","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962962542","doi":"https://doi.org/10.1109/icassp.2018.8461558","mag":"2962962542"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461558","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":"preprint","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/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":true,"raw_author_name":"Amit Das","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","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 AI and Research, Redmond, WA"],"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"],"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"],"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101814582"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":6.75112361,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.96704378,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4769","last_page":"4773"},"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":0.9987000226974487,"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":0.9980000257492065,"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/connectionism","display_name":"Connectionism","score":0.9157439470291138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8373793363571167},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.633019745349884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5957369804382324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5890103578567505},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.514805018901825},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.48935049772262573},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48611950874328613},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4665610194206238},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.44010546803474426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4380429983139038},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.42407143115997314},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.41945797204971313},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3973264694213867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3564044237136841},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35211825370788574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3387097716331482}],"concepts":[{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.9157439470291138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373793363571167},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.633019745349884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957369804382324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5890103578567505},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.514805018901825},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.48935049772262573},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48611950874328613},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4665610194206238},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44010546803474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4380429983139038},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.42407143115997314},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.41945797204971313},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3973264694213867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3564044237136841},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35211825370788574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3387097716331482},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461558","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461558","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":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1533416326","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1922655562","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2109886035","https://openalex.org/W2133564696","https://openalex.org/W2157331557","https://openalex.org/W2515801922","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2627092829","https://openalex.org/W2735006420","https://openalex.org/W2746192915","https://openalex.org/W2750499125","https://openalex.org/W2775304348","https://openalex.org/W2962742956","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963303028","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963827914","https://openalex.org/W2963953073","https://openalex.org/W2963970535","https://openalex.org/W6623517193","https://openalex.org/W6629052376","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6640090968","https://openalex.org/W6675365184","https://openalex.org/W6676562027","https://openalex.org/W6679434410","https://openalex.org/W6683258052","https://openalex.org/W6727193155","https://openalex.org/W6728030952","https://openalex.org/W6746299031","https://openalex.org/W6747398299","https://openalex.org/W6749557976","https://openalex.org/W7027429494"],"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/W68335373","https://openalex.org/W4385890381","https://openalex.org/W2402231715"],"abstract_inverted_index":{"In":[0,21],"this":[1],"study,":[2],"we":[3,23,46,60],"propose":[4],"advancing":[5],"all-neural":[6],"speech":[7],"recognition":[8],"by":[9],"directly":[10],"incorporating":[11],"attention":[12,34,44,64],"modeling":[13],"within":[14],"the":[15,38,100],"Connectionist":[16],"Temporal":[17],"Classification":[18],"(CTC)":[19],"framework.":[20],"particular,":[22],"derive":[24],"new":[25],"context":[26,70],"vectors":[27,71],"using":[28],"time":[29,74],"convolution":[30],"features":[31],"to":[32],"model":[33,97,102],"as":[35],"part":[36],"of":[37],"CTC":[39],"network.":[40],"To":[41],"further":[42],"improve":[43],"modeling,":[45],"utilize":[47],"content":[48],"information":[49],"extracted":[50],"from":[51],"a":[52,84],"network":[53],"representing":[54],"an":[55],"implicit":[56],"language":[57],"model.":[58],"Finally,":[59],"introduce":[61],"vector":[62],"based":[63],"weights":[65],"that":[66,94],"are":[67],"applied":[68],"on":[69,83],"across":[72],"both":[73],"and":[75,92],"their":[76],"individual":[77],"components.":[78],"We":[79],"evaluate":[80],"our":[81,95],"system":[82],"3400":[85],"hours":[86],"Microsoft":[87],"Cortana":[88],"voice":[89],"assistant":[90],"task":[91],"demonstrate":[93],"proposed":[96],"consistently":[98],"outperforms":[99],"baseline":[101],"achieving":[103],"about":[104],"20%":[105],"relative":[106],"reduction":[107],"in":[108],"word":[109],"error":[110],"rates.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}