{"id":"https://openalex.org/W2982640351","doi":"https://doi.org/10.1186/s13636-019-0161-0","title":"A new joint CTC-attention-based speech recognition model with multi-level multi-head attention","display_name":"A new joint CTC-attention-based speech recognition model with multi-level multi-head attention","publication_year":2019,"publication_date":"2019-10-28","ids":{"openalex":"https://openalex.org/W2982640351","doi":"https://doi.org/10.1186/s13636-019-0161-0","mag":"2982640351"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-019-0161-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0161-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0161-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0161-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071178836","display_name":"Chu-Xiong Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu-Xiong Qin","raw_affiliation_strings":["National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635256","display_name":"Wenlin Zhang","orcid":"https://orcid.org/0000-0002-6842-9722"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wen-Lin Zhang","raw_affiliation_strings":["National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101406895","display_name":"Dan Qu","orcid":"https://orcid.org/0000-0003-1688-4819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Qu","raw_affiliation_strings":["National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Digital Switching System Engineering and Technological R&D Center, Zhengzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100635256"],"corresponding_institution_ids":[],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":1.4258,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86411651,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2019","issue":"1","first_page":null,"last_page":null},"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":0.9983000159263611,"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":0.9973999857902527,"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":0.8045616149902344},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6418065428733826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6155210137367249},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5864883661270142},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5118080973625183},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5052531361579895},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.4509817361831665},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4505211114883423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4358361065387726},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4226456582546234},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42146602272987366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38890334963798523},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3051695227622986},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3023751974105835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08698654174804688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045616149902344},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6418065428733826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6155210137367249},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5864883661270142},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5118080973625183},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5052531361579895},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.4509817361831665},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4505211114883423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4358361065387726},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4226456582546234},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42146602272987366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38890334963798523},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3051695227622986},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3023751974105835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08698654174804688},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.1186/s13636-019-0161-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0161-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0161-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:17464fc86c904a17a9114d9a891854f5","is_oa":true,"landing_page_url":"https://doaj.org/article/17464fc86c904a17a9114d9a891854f5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2019, Iss 1, Pp 1-12 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-019-0161-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-019-0161-0","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-019-0161-0","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722","3091-4523"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1506193899","display_name":null,"funder_award_id":"No. 61403415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1589163256","display_name":null,"funder_award_id":"No. 61673395","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3644773272","display_name":null,"funder_award_id":"61403415","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4798291173","display_name":null,"funder_award_id":"162300410331","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G5278036591","display_name":null,"funder_award_id":"61673395","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7148560424","display_name":null,"funder_award_id":"No. 162300410331","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G7824441711","display_name":null,"funder_award_id":"2016M602975","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982640351.pdf","grobid_xml":"https://content.openalex.org/works/W2982640351.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1560013842","https://openalex.org/W1815076433","https://openalex.org/W1902237438","https://openalex.org/W2125496931","https://openalex.org/W2125838338","https://openalex.org/W2143612262","https://openalex.org/W2168103112","https://openalex.org/W2168249605","https://openalex.org/W2327501763","https://openalex.org/W2513915424","https://openalex.org/W2516196286","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2735674392","https://openalex.org/W2739883972","https://openalex.org/W2766219058","https://openalex.org/W2782451907","https://openalex.org/W2787663903","https://openalex.org/W2795935804","https://openalex.org/W2886180730","https://openalex.org/W2888867175","https://openalex.org/W2901215769","https://openalex.org/W2904818793","https://openalex.org/W2916301830","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963403664","https://openalex.org/W2963403868","https://openalex.org/W2963447639","https://openalex.org/W2964308564","https://openalex.org/W3104486441","https://openalex.org/W6600662924","https://openalex.org/W6601337496","https://openalex.org/W6631814027","https://openalex.org/W6739901393","https://openalex.org/W6828894009"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2146544734"],"abstract_inverted_index":{"Abstract":[0],"A":[1,21],"method":[2,97,111,153],"called":[3],"joint":[4,61],"connectionist":[5],"temporal":[6],"classification":[7],"(CTC)-attention-based":[8],"speech":[9],"recognition":[10],"has":[11,17],"recently":[12],"received":[13],"increasing":[14],"focus":[15],"and":[16,54,83,139],"achieved":[18],"impressive":[19],"performance.":[20],"hybrid":[22,76],"end-to-end":[23,45,144,160],"architecture":[24],"that":[25,94,109,118,151],"adds":[26],"an":[27],"extra":[28,37],"CTC":[29],"loss":[30],"to":[31,50,157],"the":[32,44,51,95,127,158],"attention-based":[33],"model":[34,62],"could":[35],"force":[36],"restrictions":[38],"on":[39,91,106,134,148],"alignments.":[40],"To":[41],"explore":[42],"better":[43],"models,":[46],"we":[47,58,72],"propose":[48],"improvements":[49],"feature":[52],"extraction":[53],"attention":[55,77,85],"mechanism.":[56],"First,":[57],"introduce":[59],"a":[60,75,113,135],"trained":[63,133],"with":[64,101],"nonnegative":[65],"matrix":[66],"factorization":[67],"(NMF)-based":[68],"high-level":[69],"features.":[70],"Then,":[71],"put":[73],"forward":[74],"mechanism":[78],"by":[79],"incorporating":[80],"multi-head":[81],"attentions":[82],"calculating":[84],"scores":[86],"over":[87],"multi-level":[88],"outputs.":[89],"Experiments":[90,105],"TIMIT":[92],"indicate":[93],"new":[96],"achieves":[98],"state-of-the-art":[99,159],"performance":[100],"our":[102,110,152],"best":[103,128],"model.":[104],"WSJ":[107],"show":[108,150],"exhibits":[112],"word":[114],"error":[115],"rate":[116],"(WER)":[117],"is":[119,132,154],"only":[120],"0.2%":[121],"worse":[122],"in":[123,162],"absolute":[124],"value":[125],"than":[126],"referenced":[129],"method,":[130],"which":[131],"much":[136],"larger":[137],"dataset,":[138],"it":[140],"beats":[141],"all":[142],"present":[143],"methods.":[145],"Further":[146],"experiments":[147],"LibriSpeech":[149],"also":[155],"comparable":[156],"system":[161],"WER.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}