{"id":"https://openalex.org/W4391021649","doi":"https://doi.org/10.1109/asru57964.2023.10389631","title":"Spike-Triggered Contextual Biasing for End-to-End Mandarin Speech Recognition","display_name":"Spike-Triggered Contextual Biasing for End-to-End Mandarin Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021649","doi":"https://doi.org/10.1109/asru57964.2023.10389631"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100608028","display_name":"Kaixun Huang","orcid":"https://orcid.org/0000-0001-7498-4397"},"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":"Kaixun Huang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437589","display_name":"Ao Zhang","orcid":"https://orcid.org/0000-0002-1536-2413"},"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":"Ao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449716","display_name":"Binbin Zhang","orcid":"https://orcid.org/0000-0002-7164-5127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binbin Zhang","raw_affiliation_strings":["WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085413616","display_name":"Tianyi Xu","orcid":"https://orcid.org/0009-0001-5332-8881"},"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":"Tianyi Xu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074833963","display_name":"Xingchen Song","orcid":"https://orcid.org/0009-0009-9516-5361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingchen Song","raw_affiliation_strings":["WeNet Open Source Community"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WeNet Open Source Community","institution_ids":[]}]},{"author_position":"last","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":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU),Xian,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63119316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9986000061035156,"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":0.9945999979972839,"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":0.7747546434402466},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.65228271484375},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5997486710548401},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.596798300743103},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5609510540962219},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.5438559055328369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5226028561592102},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43573105335235596},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33797943592071533},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1521058976650238},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08771342039108276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08090361952781677},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0792371928691864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7747546434402466},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.65228271484375},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5997486710548401},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.596798300743103},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5609510540962219},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.5438559055328369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5226028561592102},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43573105335235596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33797943592071533},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1521058976650238},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08771342039108276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08090361952781677},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0792371928691864},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/asru57964.2023.10389631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":28,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2127141656","https://openalex.org/W2157331557","https://openalex.org/W2327501763","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2903250132","https://openalex.org/W2962760690","https://openalex.org/W3097239815","https://openalex.org/W3097794466","https://openalex.org/W3097874139","https://openalex.org/W3160405885","https://openalex.org/W3160413945","https://openalex.org/W3162639446","https://openalex.org/W3198004110","https://openalex.org/W4224918838","https://openalex.org/W4225289150","https://openalex.org/W4225985539","https://openalex.org/W4226462878","https://openalex.org/W4319862261","https://openalex.org/W4372259757","https://openalex.org/W4372259807","https://openalex.org/W4385822246","https://openalex.org/W4385822295","https://openalex.org/W4385823371","https://openalex.org/W6623517193","https://openalex.org/W6675365184","https://openalex.org/W6767876487"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"The":[0],"attention-based":[1],"deep":[2,40,63],"contextual":[3,24,45,103,134],"biasing":[4,41,64],"method":[5,65],"has":[6],"been":[7],"demonstrated":[8],"to":[9,50,122],"effectively":[10],"improve":[11,101],"the":[12,34,37,52,102,109,123],"recognition":[13,19],"performance":[14],"of":[15,36,54],"end-to-end":[16],"automatic":[17],"speech":[18],"(ASR)":[20],"systems":[21],"on":[22,108,133],"given":[23],"phrases.":[25,135],"However,":[26],"unlike":[27],"shallow":[28,86],"fusion":[29,87],"methods":[30,42,88],"that":[31,66],"directly":[32],"bias":[33,76],"posterior":[35],"ASR":[38],"model,":[39,125],"implicitly":[43],"integrate":[44],"information,":[46],"making":[47],"it":[48],"challenging":[49],"control":[51],"degree":[53],"bias.":[55,73],"In":[56],"this":[57],"study,":[58],"we":[59,93],"introduce":[60],"a":[61,95,116],"spike-triggered":[62],"simultaneously":[67],"supports":[68],"both":[69,75],"explicit":[70],"and":[71,81,100],"implicit":[72],"Moreover,":[74],"approaches":[77],"exhibit":[78],"significant":[79],"improvements":[80],"can":[82],"be":[83],"cascaded":[84],"with":[85,126],"for":[89],"better":[90],"results.":[91],"Furthermore,":[92],"propose":[94],"context":[96],"sampling":[97],"enhancement":[98],"strategy":[99],"phrase":[104],"filtering":[105],"algorithm.":[106],"Experiments":[107],"public":[110],"WenetSpeech":[111],"Mandarin":[112],"biased-word":[113],"dataset":[114],"show":[115],"32.0%":[117],"relative":[118,130],"CER":[119,131],"reduction":[120,132],"compared":[121],"baseline":[124],"an":[127],"impressively":[128],"68.6%":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
