{"id":"https://openalex.org/W4225644313","doi":"https://doi.org/10.1109/asru51503.2021.9688238","title":"Boundary and Context Aware Training for CIF-Based Non-Autoregressive End-to-End ASR","display_name":"Boundary and Context Aware Training for CIF-Based Non-Autoregressive End-to-End ASR","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4225644313","doi":"https://doi.org/10.1109/asru51503.2021.9688238"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9688238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688238","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100616400","display_name":"Fan Yu","orcid":"https://orcid.org/0000-0002-0576-7396"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fan Yu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088820402","display_name":"Haoneng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoneng Luo","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102543677","display_name":"Yuhao Liang","orcid":"https://orcid.org/0009-0008-9516-6594"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Liang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109482068","display_name":"Zhuoyuan Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoyuan Yao","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China"],"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,Xi'an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068298033","display_name":"Yingying Gao","orcid":"https://orcid.org/0000-0002-6869-3013"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Gao","raw_affiliation_strings":["China Mobile Research Institute"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067650083","display_name":"Leijing Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leijing Hou","raw_affiliation_strings":["China Mobile Research Institute"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032367559","display_name":"Shilei Zhang","orcid":"https://orcid.org/0000-0001-8169-0098"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["China Mobile Research Institute"],"affiliations":[{"raw_affiliation_string":"China Mobile Research Institute","institution_ids":["https://openalex.org/I180662265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100616400"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.1309,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82277061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"328","last_page":"334"},"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":0.9975000023841858,"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/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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":0.8661291599273682},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6600440144538879},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6530028581619263},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6353742480278015},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5907833576202393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5396175384521484},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44782203435897827},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.44343990087509155},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.4200797975063324},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4123140871524811},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32844823598861694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2365202009677887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8661291599273682},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6600440144538879},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6530028581619263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6353742480278015},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5907833576202393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5396175384521484},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44782203435897827},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.44343990087509155},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4200797975063324},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4123140871524811},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32844823598861694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2365202009677887},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9688238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9688238","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2526425061","https://openalex.org/W2755682845","https://openalex.org/W2767206889","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962824709","https://openalex.org/W2963242190","https://openalex.org/W2963434219","https://openalex.org/W2970832665","https://openalex.org/W3016167541","https://openalex.org/W3023751411","https://openalex.org/W3035445001","https://openalex.org/W3096160024","https://openalex.org/W3097625183","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3105169251","https://openalex.org/W3151526698","https://openalex.org/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3163793923","https://openalex.org/W3198522318","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6750226204","https://openalex.org/W6754299077","https://openalex.org/W6754473786","https://openalex.org/W6767366528","https://openalex.org/W6774835902","https://openalex.org/W6777217127","https://openalex.org/W6779752190"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W2053269318","https://openalex.org/W2546021431","https://openalex.org/W2581127593"],"abstract_inverted_index":{"Continuous":[0],"integrate-and-fire":[1],"(CIF)":[2],"based":[3,69],"models,":[4],"which":[5],"use":[6],"a":[7,60,110,115,140,154,185],"soft":[8],"and":[9,62,177],"monotonic":[10],"alignment":[11,33],"mechanism,":[12],"have":[13],"been":[14],"well":[15,50],"applied":[16],"in":[17,89],"non-autoregressive":[18],"(NAR)":[19],"speech":[20],"recognition":[21],"with":[22,26,148,153],"competitive":[23],"performance":[24],"compared":[25,152],"other":[27,174],"NAR":[28,70,175],"methods.":[29],"However,":[30],"such":[31],"an":[32,39,93,164],"learning":[34,85],"strategy":[35],"may":[36],"suffer":[37],"from":[38],"erroneous":[40],"acoustic":[41,87,125],"boundary":[42,61],"estimation,":[43],"severely":[44],"hindering":[45],"the":[46,52,73,84,90,100,106,122,129,136,180],"convergence":[47],"speed":[48],"as":[49,51],"system":[53],"performance.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,113],"propose":[59],"context":[63],"aware":[64],"training":[65],"approach":[66],"for":[67],"CIF":[68,101],"models.":[71],"Firstly,":[72],"connectionist":[74],"temporal":[75],"classification":[76],"(CTC)":[77],"spike":[78],"information":[79],"is":[80,97],"utilized":[81],"to":[82,104,120],"guide":[83],"of":[86,124,146],"boundaries":[88],"CIF.":[91],"Besides,":[92],"additional":[94],"contextual":[95],"decoder":[96],"introduced":[98],"behind":[99],"decoder,":[102],"aiming":[103],"capture":[105],"linguistic":[107],"dependencies":[108],"within":[109],"sentence.":[111],"Finally,":[112],"adopt":[114],"recently":[116],"proposed":[117,137],"Conformer":[118,158,182],"architecture":[119],"improve":[121],"capacity":[123],"modeling.":[126],"Experiments":[127],"on":[128,163,184],"open-source":[130],"Mandarin":[131,168],"AISHELL-1":[132],"corpus":[133],"show":[134],"that":[135],"method":[138],"achieves":[139],"comparable":[141],"character":[142],"error":[143],"rates":[144],"(CERs)":[145],"4.9%":[147],"only":[149],"1/24":[150],"latency":[151],"state-of-the-art":[155],"autoregressive":[156],"(AR)":[157],"model.":[159],"Futhermore,":[160],"when":[161],"evaluating":[162],"internal":[165],"7500":[166],"hours":[167],"corpus,":[169],"our":[170],"model":[171,183],"still":[172],"outperforms":[173],"methods":[176],"even":[178],"reaches":[179],"AR":[181],"challenging":[186],"real-world":[187],"noisy":[188],"test":[189],"set.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}