{"id":"https://openalex.org/W3012121909","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023020","title":"Bidirectional Temporal Convolution with Self-Attention Network for CTC-Based Acoustic Modeling","display_name":"Bidirectional Temporal Convolution with Self-Attention Network for CTC-Based Acoustic Modeling","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3012121909","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023020","mag":"3012121909"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023020","is_oa":false,"landing_page_url":"http://doi.org/10.1109/apsipaasc47483.2019.9023020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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":"https://openalex.org/A5004183775","display_name":"Jian Sun","orcid":"https://orcid.org/0000-0001-6530-9007"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jian Sun","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":["University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,National Engineering Laboratory for Speech and Language Information Processing,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100463079","display_name":"Yao Liu","orcid":"https://orcid.org/0000-0002-5271-0536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Liu","raw_affiliation_strings":["China General Technology Research Institute"],"affiliations":[{"raw_affiliation_string":"China General Technology Research Institute","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004183775"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60634024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1262","last_page":"1266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9973999857902527,"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/upsampling","display_name":"Upsampling","score":0.8715499639511108},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8351823091506958},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6902896165847778},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6311599016189575},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5614541172981262},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5521848201751709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5293774604797363},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.47759151458740234},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4295822083950043},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.4108869433403015},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3711279630661011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3398464322090149}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.8715499639511108},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351823091506958},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6902896165847778},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6311599016189575},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5614541172981262},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5521848201751709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5293774604797363},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.47759151458740234},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4295822083950043},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.4108869433403015},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3711279630661011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3398464322090149},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023020","is_oa":false,"landing_page_url":"http://doi.org/10.1109/apsipaasc47483.2019.9023020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2005708641","https://openalex.org/W2125964738","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2593910181","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2792764867","https://openalex.org/W2798858969","https://openalex.org/W2888957520","https://openalex.org/W2889163603","https://openalex.org/W2892009249","https://openalex.org/W2962778134","https://openalex.org/W2962824709","https://openalex.org/W2963211739","https://openalex.org/W2963226322","https://openalex.org/W2963403664","https://openalex.org/W2963970535","https://openalex.org/W2964089206","https://openalex.org/W2964330921","https://openalex.org/W4295253143","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638749077","https://openalex.org/W6696934422","https://openalex.org/W6734241735","https://openalex.org/W6739901393","https://openalex.org/W6749825310","https://openalex.org/W6751097180"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W1997922073","https://openalex.org/W2281134365"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1,72],"classification":[2],"(CTC)":[3],"based":[4],"on":[5],"recurrent":[6],"(RNNs)":[7],"or":[8],"convolutional":[9],"neural":[10],"networks":[11],"(CNNs)":[12],"is":[13,78],"a":[14,128],"method":[15],"for":[16,54],"end-to-end":[17],"acoustic":[18,45],"modeling.":[19],"Inspired":[20],"by":[21],"the":[22,26,41,62,85,93,101,119,133,136],"recent":[23],"success":[24],"of":[25,68,90],"self-attention":[27,75],"network":[28,76],"(SAN)":[29],"in":[30,47,80,100,104,132],"machine":[31],"translation":[32],"and":[33,65,87,95,110],"other":[34],"domains":[35],"such":[36],"as":[37],"images,":[38],"we":[39],"apply":[40],"SAN":[42,50],"to":[43,82,106],"CTC":[44,138],"modeling":[46],"this":[48],"paper.":[49],"has":[51],"powerful":[52],"capabilities":[53],"capturing":[55],"global":[56,86],"dependencies,":[57],"but":[58],"it":[59],"cannot":[60],"model":[61],"sequential":[63],"information":[64],"local":[66,88],"interactions":[67],"utterances.":[69,91],"The":[70,123],"bidirectional":[71],"convolution":[73],"with":[74],"(BTCSAN)":[77],"proposed":[79,102,124],"order":[81,105],"capture":[83],"both":[84],"dependencies":[89],"Furthermore,":[92],"down-":[94],"upsampling":[96],"strategies":[97],"are":[98,115],"adopted":[99],"BTCSAN":[103,125],"achieve":[107],"computational":[108],"efficiency":[109],"high":[111],"recognition":[112],"accuracy.":[113],"Experiments":[114],"carried":[116],"out":[117],"using":[118],"King-ASR-117":[120],"Japanese":[121],"corpus.":[122],"can":[126],"obtain":[127],"15.87%":[129],"relative":[130],"improvement":[131],"CER":[134],"over":[135],"BLSTM-based":[137],"baseline.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}