{"id":"https://openalex.org/W4405709896","doi":"https://doi.org/10.1109/iscslp63861.2024.10800193","title":"Dual-Strategy Fusion Method in Noise-Robust Speech Recognition","display_name":"Dual-Strategy Fusion Method in Noise-Robust Speech Recognition","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709896","doi":"https://doi.org/10.1109/iscslp63861.2024.10800193"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5100328393","display_name":"Jiahao Li","orcid":"https://orcid.org/0000-0003-4559-0086"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiahao Li","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037493212","display_name":"Cunhang Fan","orcid":"https://orcid.org/0000-0001-6318-8803"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cunhang Fan","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115613901","display_name":"Enrui Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enrui Liu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067137933","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-6509-5520"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101578581","display_name":"Zhao Lv","orcid":"https://orcid.org/0000-0001-9727-366X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Lv","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University,Anhui Province Key Laboratory of Multimodal Cognitive Computation,Hefei","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100328393"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.3735,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61241099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8234999775886536,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8234999775886536,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.8029000163078308,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8015999794006348,"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":0.6961483955383301},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6956765055656433},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.56175297498703},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5313680171966553},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5180345177650452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4276845157146454},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39226704835891724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6961483955383301},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956765055656433},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.56175297498703},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5313680171966553},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5180345177650452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4276845157146454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39226704835891724},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800193","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1322201508","display_name":null,"funder_award_id":"62201002,6247077204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4811154608","display_name":null,"funder_award_id":"2021ZD0201500","funder_id":"https://openalex.org/F4320312987","funder_display_name":"Social Trends Institute"}],"funders":[{"id":"https://openalex.org/F4320312987","display_name":"Social Trends Institute","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2062164080","https://openalex.org/W2127141656","https://openalex.org/W2128653836","https://openalex.org/W2153894152","https://openalex.org/W2296167893","https://openalex.org/W2406395231","https://openalex.org/W2766219058","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2972436155","https://openalex.org/W3015912787","https://openalex.org/W3096408984","https://openalex.org/W3097777922","https://openalex.org/W3109196171","https://openalex.org/W3206531472","https://openalex.org/W4375869466","https://openalex.org/W4376456759","https://openalex.org/W4380434618","https://openalex.org/W4385822407","https://openalex.org/W4386234565","https://openalex.org/W4388017359","https://openalex.org/W4391892525","https://openalex.org/W4392904386","https://openalex.org/W4392909789","https://openalex.org/W4402111732","https://openalex.org/W6638749077"],"related_works":["https://openalex.org/W2317351040","https://openalex.org/W2952466936","https://openalex.org/W1988622314","https://openalex.org/W2393949104","https://openalex.org/W2099421762","https://openalex.org/W4236344264","https://openalex.org/W3046201198","https://openalex.org/W2530546662","https://openalex.org/W4293061921","https://openalex.org/W2967030268"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1,36],"Recognition":[2],"(ASR)":[3],"systems":[4],"have":[5],"become":[6],"in-tegral":[7],"to":[8,29,34,99,145],"various":[9,97],"aspects":[10],"of":[11,17,80,103],"people's":[12],"lives.":[13],"However,":[14],"the":[15,101,110,137],"presence":[16],"noise":[18,118],"in":[19],"real-world":[20],"environments":[21],"often":[22],"affects":[23],"ASR":[24,53,65,134],"performance.":[25,54],"The":[26,75,124],"mainstream":[27],"approach":[28],"mitigate":[30],"this":[31,44,57,59],"issue":[32],"is":[33],"use":[35],"Enhancement":[37],"(SE)":[38],"as":[39],"a":[40,68],"preprocessing":[41],"step.":[42],"Nevertheless,":[43],"process":[45],"inevitably":[46],"introduces":[47],"speech":[48,104,113],"distortion,":[49],"which":[50],"further":[51],"degrades":[52],"To":[55],"address":[56],"problem,":[58],"paper":[60],"proposes":[61],"an":[62],"end-to-end":[63],"robust":[64],"framework":[66],"with":[67],"dual-strategy":[69,76],"fusion":[70,77],"method":[71,78,131],"for":[72],"joint":[73,147],"training.":[74],"consist":[79],"Mask":[81],"and":[82,86,116,122],"Mapping":[83],"Fusion":[84,89],"(MMF)":[85],"Interactive":[87],"Feature":[88],"(IFF).":[90],"These":[91],"strategies":[92],"integrate":[93],"different":[94],"features":[95],"at":[96],"stages":[98],"reduce":[100],"impact":[102],"distortion.":[105],"We":[106],"conducted":[107],"experiments":[108],"on":[109],"open-source":[111],"Mandarin":[112],"corpus":[114],"AISHELL-1":[115],"two":[117],"datasets,":[119],"100":[120],"Nonspeech":[121],"NOISEX-92.":[123],"experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"our":[129],"proposed":[130],"significantly":[132],"improves":[133],"performance,":[135],"reducing":[136],"character":[138],"error":[139],"rate":[140],"(CER)":[141],"by":[142],"17.27%":[143],"compared":[144],"traditional":[146],"training":[148],"methods.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}