{"id":"https://openalex.org/W4206468315","doi":"https://doi.org/10.1109/icct52962.2021.9657881","title":"A Chinese Speech Recognition System Based on Fusion Network Structure","display_name":"A Chinese Speech Recognition System Based on Fusion Network Structure","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W4206468315","doi":"https://doi.org/10.1109/icct52962.2021.9657881"},"language":"en","primary_location":{"id":"doi:10.1109/icct52962.2021.9657881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct52962.2021.9657881","pdf_url":null,"source":{"id":"https://openalex.org/S4363607878","display_name":"2021 IEEE 21st International Conference on Communication Technology (ICCT)","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 21st International Conference on Communication Technology (ICCT)","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/A5104025712","display_name":"Lunvi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lunvi Guo","raw_affiliation_strings":["School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078085083","display_name":"Shining Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shining Mu","raw_affiliation_strings":["School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078023373","display_name":"Chaofan Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaofan Shi","raw_affiliation_strings":["School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081115024","display_name":"Bo Yan","orcid":"https://orcid.org/0000-0003-0256-9682"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yan","raw_affiliation_strings":["School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110836840","display_name":"Zhouling Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouling Xiao","raw_affiliation_strings":["School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004259273","display_name":"Sheng Yu","orcid":"https://orcid.org/0009-0008-3460-0772"},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Yu","raw_affiliation_strings":["Optical Network System UTStarcom Telecom. Ltd., Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Optical Network System UTStarcom Telecom. Ltd., Hangzhou, China","institution_ids":["https://openalex.org/I4210136246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104025712"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.3441,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58428475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"1271","last_page":"1276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9952999949455261,"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":0.9876000285148621,"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/speech-recognition","display_name":"Speech recognition","score":0.8080793619155884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032106161117554},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6733957529067993},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6533370614051819},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6213239431381226},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5103086829185486},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47156140208244324},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46871939301490784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4617730379104614},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44958260655403137},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4394654333591461},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4391973912715912},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43859216570854187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3645228147506714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3355940878391266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0732639729976654}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8080793619155884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032106161117554},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6733957529067993},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6533370614051819},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6213239431381226},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5103086829185486},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47156140208244324},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46871939301490784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4617730379104614},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44958260655403137},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4394654333591461},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4391973912715912},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43859216570854187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3645228147506714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3355940878391266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0732639729976654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icct52962.2021.9657881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icct52962.2021.9657881","pdf_url":null,"source":{"id":"https://openalex.org/S4363607878","display_name":"2021 IEEE 21st International Conference on Communication Technology (ICCT)","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 21st International Conference on Communication Technology (ICCT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7017687580","display_name":null,"funder_award_id":"61973056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"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":27,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1920769845","https://openalex.org/W1979001355","https://openalex.org/W2086602917","https://openalex.org/W2097117768","https://openalex.org/W2127141656","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2293858598","https://openalex.org/W2394932179","https://openalex.org/W2770454110","https://openalex.org/W2802488037","https://openalex.org/W2810350850","https://openalex.org/W2936774411","https://openalex.org/W2944150351","https://openalex.org/W2945616452","https://openalex.org/W2951559648","https://openalex.org/W2964350391","https://openalex.org/W2972909277","https://openalex.org/W2973202379","https://openalex.org/W2981899103","https://openalex.org/W3128230564","https://openalex.org/W4253573210","https://openalex.org/W6640598943","https://openalex.org/W6694260854","https://openalex.org/W6766618836","https://openalex.org/W7104178341"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2145230572","https://openalex.org/W2166312020","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W4385611764","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"The":[0,85,133],"purpose":[1],"of":[2,130],"an":[3],"automatic":[4,46],"speech":[5,11,39,47,67,105],"recognition":[6,48],"system":[7,49],"is":[8,16,87,118],"to":[9,81],"convert":[10,104],"into":[12,107],"recognizable":[13],"text.":[14],"Chinese":[15,38,45,108],"a":[17,44,70,99],"language":[18,62],"in":[19],"which":[20,102,142],"the":[21,52,66,75,83,113,123,127,148],"same":[22],"pronunciation":[23],"but":[24],"different":[25,28],"writing":[26],"means":[27],"meanings.":[29],"At":[30],"present,":[31],"there":[32],"are":[33,138,143],"relatively":[34],"few":[35],"researches":[36],"on":[37,51,98,122],"recognition.":[40],"Therefore,":[41],"we":[42],"propose":[43],"based":[50,97],"fusion":[53],"network":[54],"RRAINet":[55],"and":[56,73,78,95,120,126,140],"End-to-End":[57],"structure":[58],"acoustic":[59],"model":[60,86,114,134],"&#x002B;":[61],"model.":[63,151],"We":[64],"treat":[65],"signal":[68],"as":[69],"visual":[71],"problem,":[72],"use":[74],"Mel":[76],"spectrum":[77],"SpecAugment":[79],"methods":[80],"preprocess":[82],"data.":[84],"trained":[88],"by":[89],"connected":[90],"time":[91],"series":[92],"classification":[93],"criteria":[94],"decoded":[96],"greedy":[100],"algorithm,":[101],"can":[103],"signals":[106],"characters.":[109],"Experiments":[110],"show":[111],"that":[112],"phoneme":[115],"error":[116,136],"rate":[117],"12.56&#x0025;":[119],"12.38&#x0025;":[121],"dev":[124],"set":[125,129],"test":[128],"Free":[131],"ST(ST-CMDS-20170001_1-OS).":[132],"word":[135],"rates":[137],"18.79<sup>&#x0025;</sup>":[139],"18.74&#x0025;,":[141],"about":[144],"5&#x0025;":[145],"lower":[146],"than":[147],"baseline":[149],"VGG-CTC":[150]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}