{"id":"https://openalex.org/W2913196735","doi":"https://doi.org/10.1109/slt.2018.8639675","title":"Improving Very Deep Time-Delay Neural Network With Vertical-Attention For Effectively Training CTC-Based ASR Systems","display_name":"Improving Very Deep Time-Delay Neural Network With Vertical-Attention For Effectively Training CTC-Based ASR Systems","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913196735","doi":"https://doi.org/10.1109/slt.2018.8639675","mag":"2913196735"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486855","display_name":"Peng Shen","orcid":"https://orcid.org/0000-0002-0137-2629"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Peng Shen","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"25","issue":null,"first_page":"77","last_page":"83"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.8429234027862549},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6900442838668823},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6367076635360718},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6081934571266174},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.601410448551178},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5837658643722534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4682909846305847},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45988500118255615},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3557215929031372},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11835870146751404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8429234027862549},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6900442838668823},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6367076635360718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6081934571266174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.601410448551178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5837658643722534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4682909846305847},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45988500118255615},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3557215929031372},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11835870146751404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2018.8639675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728250","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930704","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W87954838","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2102113734","https://openalex.org/W2117671523","https://openalex.org/W2127141656","https://openalex.org/W2168231600","https://openalex.org/W2181607856","https://openalex.org/W2194775991","https://openalex.org/W2201092681","https://openalex.org/W2208299922","https://openalex.org/W2327501763","https://openalex.org/W2397947827","https://openalex.org/W2402146185","https://openalex.org/W2405883473","https://openalex.org/W2515753980","https://openalex.org/W2515801922","https://openalex.org/W2515863432","https://openalex.org/W2516183504","https://openalex.org/W2530876040","https://openalex.org/W2541674938","https://openalex.org/W2569520850","https://openalex.org/W2627092829","https://openalex.org/W2682975603","https://openalex.org/W2802023636","https://openalex.org/W2888957520","https://openalex.org/W2963211739","https://openalex.org/W2963403868","https://openalex.org/W2963410064","https://openalex.org/W2963654251","https://openalex.org/W2964121744","https://openalex.org/W3034729383","https://openalex.org/W4385245566","https://openalex.org/W6603550504","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6684859321","https://openalex.org/W6687630728","https://openalex.org/W6688039610","https://openalex.org/W6712816420","https://openalex.org/W6712930963","https://openalex.org/W6729059855","https://openalex.org/W6739901393","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"The":[0],"very":[1,57],"deep":[2,43,58,70,95],"neural":[3,62],"network":[4,63],"has":[5,17,30],"recently":[6],"been":[7],"proposed":[8,157],"for":[9,20,50,80,97],"speech":[10],"recognition":[11,153],"and":[12,45,132,163,167],"achieves":[13],"significant":[14],"performance.":[15,87],"It":[16],"excellent":[18],"potential":[19,33],"integration":[21],"with":[22,73,102,124],"end-to-end":[23],"(E2E)":[24],"training.":[25],"Connectionist":[26],"temporal":[27],"classification":[28],"(CTC)":[29],"shown":[31],"great":[32],"in":[34],"E2E":[35,119],"acoustic":[36,52,126],"modeling.":[37,53],"In":[38],"this":[39,130],"study,":[40],"we":[41,138],"investigate":[42],"architectures":[44],"techniques":[46],"which":[47],"are":[48],"suitable":[49,69],"CTC-based":[51],"We":[54],"propose":[55],"a":[56,68],"residual":[59,146],"time-delay":[60],"CTC":[61,75,169],"(VResTD-CTC).":[64],"How":[65],"to":[66,112,143],"select":[67],"architecture":[71,96],"optimized":[72,107],"the":[74,82,85,135,140,145,161],"objective":[76],"function":[77],"is":[78],"crucial":[79],"obtaining":[81],"state":[83],"of":[84],"art":[86],"Excellent":[88],"performances":[89,117],"can":[90],"be":[91],"obtained":[92],"by":[93],"selecting":[94],"non-E2E":[98],"ASR":[99],"systems":[100,122],"modeling":[101,123],"tied-triphone":[103],"states.":[104],"However,":[105],"these":[106],"structures":[108],"do":[109],"not":[110],"guarantee":[111],"achieve":[113],"better":[114],"or":[115],"comparable":[116],"on":[118],"(e.g.,":[120],"CTC-based)":[121],"dynamic":[125],"units.":[127],"For":[128],"solving":[129],"problem":[131],"further":[133],"leveraging":[134],"system":[136],"performance,":[137],"introduce":[139],"vertical-attention":[141],"mechanism":[142],"reweight":[144],"blocks":[147],"at":[148],"each":[149],"time":[150],"step.":[151],"Speech":[152],"experiments":[154],"show":[155],"our":[156],"model":[158],"significantly":[159],"outperforms":[160],"DNN":[162],"LSTM-based":[164],"(both":[165],"bidirectional":[166],"unidirectional)":[168],"baseline":[170],"models.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}