{"id":"https://openalex.org/W2896092870","doi":"https://doi.org/10.1109/ijcnn.2018.8489589","title":"Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition","display_name":"Syllable-Based Acoustic Modeling with CTC for Multi-Scenarios Mandarin speech recognition","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2896092870","doi":"https://doi.org/10.1109/ijcnn.2018.8489589","mag":"2896092870"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","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/A5101995701","display_name":"Yuanyuan Zhao","orcid":"https://orcid.org/0000-0002-6107-2185"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Zhao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000236213","display_name":"Linhao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhao Dong","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004363895","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-3576-6914"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065635207","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-6379-7617"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, P.R.China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"19","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":0.9994000196456909,"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":0.9994000196456909,"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":0.9944999814033508,"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":0.983299970626831,"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":0.8458898067474365},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.745256781578064},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.5647563934326172},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5384611487388611},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.521759569644928},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4608911871910095},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4550718367099762},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4408690929412842},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43830546736717224},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4375641345977783},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4183759391307831},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.413677453994751},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41160112619400024},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3318156599998474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32944947481155396},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15017759799957275},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09786564111709595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458898067474365},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.745256781578064},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.5647563934326172},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5384611487388611},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.521759569644928},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4608911871910095},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4550718367099762},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4408690929412842},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43830546736717224},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4375641345977783},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4183759391307831},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.413677453994751},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41160112619400024},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3318156599998474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32944947481155396},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15017759799957275},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09786564111709595},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/ijcnn.2018.8489589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1525636403","https://openalex.org/W1542280630","https://openalex.org/W1600744878","https://openalex.org/W1774234760","https://openalex.org/W1974979586","https://openalex.org/W1986184096","https://openalex.org/W1989674786","https://openalex.org/W1995562189","https://openalex.org/W2013598660","https://openalex.org/W2046726504","https://openalex.org/W2057653135","https://openalex.org/W2077450519","https://openalex.org/W2087402357","https://openalex.org/W2099621636","https://openalex.org/W2110798204","https://openalex.org/W2112739286","https://openalex.org/W2121464381","https://openalex.org/W2132658536","https://openalex.org/W2140130847","https://openalex.org/W2144499799","https://openalex.org/W2155273149","https://openalex.org/W2158069733","https://openalex.org/W2167200294","https://openalex.org/W2193413348","https://openalex.org/W2395106899","https://openalex.org/W2395416438","https://openalex.org/W2398826216","https://openalex.org/W2406395231","https://openalex.org/W2407080277","https://openalex.org/W2407146636","https://openalex.org/W2530876040","https://openalex.org/W2627092829","https://openalex.org/W2748163763","https://openalex.org/W2758625301","https://openalex.org/W2767353373","https://openalex.org/W2786031273","https://openalex.org/W2787133659","https://openalex.org/W2962909949","https://openalex.org/W2963211739","https://openalex.org/W6675409298","https://openalex.org/W6676481782","https://openalex.org/W6687566353","https://openalex.org/W6711850222","https://openalex.org/W6712560600","https://openalex.org/W6713762819","https://openalex.org/W6713806900","https://openalex.org/W6713954808","https://openalex.org/W6739366949","https://openalex.org/W6745762954","https://openalex.org/W6748086369","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2992378684","https://openalex.org/W2125343999","https://openalex.org/W4200200210","https://openalex.org/W2161188302"],"abstract_inverted_index":{"With":[0],"the":[1,52,84,90,116,132,143,154,179,188,201,206,218],"improvement":[2,235],"of":[3,14,44,57,79,92,118,203],"speech":[4,81],"recognition,":[5],"voice":[6,58],"products":[7],"are":[8,23],"gradually":[9],"applied":[10],"to":[11,19,25,114,123],"every":[12],"scene":[13],"life.":[15],"The":[16,41,213],"existing":[17],"approaches":[18,46],"handle":[20],"various":[21],"scenarios":[22,78,226],"often":[24],"build":[26],"many":[27],"different":[28],"acoustic":[29,64,138,222],"models":[30],"using":[31],"scenario-dependent":[32],"data":[33,185,239,242],"only,":[34],"with":[35,71,245],"each":[36],"for":[37,76,224,236],"a":[38,96,128,195],"special":[39],"scene.":[40,98],"obvious":[42],"weakness":[43],"these":[45],"is":[47,74,111,164,168],"that":[48,109,146,217],"it":[49,100,167],"seriously":[50],"hampers":[51],"large-scale":[53],"application":[54],"and":[55,121,166,172,183,193,209,232,240],"maintenance":[56],"products.":[59],"To":[60],"address":[61],"this":[62],"issue,":[63],"modeling":[65,88,94,107],"based":[66,199],"on":[67,200],"context-independent":[68,87],"syllables":[69,152],"optimized":[70],"CTC":[72,221],"loss":[73],"presented":[75],"multiple":[77,225],"Mandarin":[80],"recognition.":[82],"On":[83,131],"one":[85],"hand,":[86,134],"overcomes":[89],"shortcomings":[91],"context-dependent":[93,106,147],"overfitting":[95],"particular":[97],"Also,":[99,151],"sidesteps":[101],"decision":[102,119],"trees":[103],"used":[104],"in":[105,127,153,205],"so":[108],"there":[110],"no":[112],"need":[113],"consider":[115],"building":[117],"tree":[120],"whether":[122],"start":[124],"training":[125,197],"again":[126],"real":[129],"application.":[130],"other":[133],"choosing":[135],"longer-length":[136],"syllable":[137],"units":[139],"can":[140,149,227],"effectively":[141],"preserve":[142],"co-articulation":[144],"effect":[145],"phone":[148,238],"model.":[150],"Chinese":[155],"language":[156],"have":[157],"its":[158,162],"inherent":[159],"advantages,":[160],"as":[161],"number":[163],"fixed":[165],"trainable,":[169],"effective":[170],"generalization":[171],"better":[173],"robustness.":[174],"This":[175],"paper":[176],"also":[177],"explores":[178],"differences":[180],"between":[181],"wideband":[182],"narrowband":[184],"caused":[186],"by":[187],"front-end":[189],"signal":[190],"acquisition":[191],"block,":[192],"proposes":[194],"unified":[196],"method":[198],"use":[202],"VGG":[204],"bottom":[207],"layer,":[208],"introduces":[210],"layer":[211],"normalization.":[212],"experimental":[214],"results":[215],"demonstrate":[216],"proposed":[219],"syllable-based":[220],"model":[223],"achieve":[228],"more":[229],"than":[230],"15%":[231],"7%":[233],"relatively":[234],"mobile":[237],"telephone":[241],"separately":[243],"compare":[244],"scenarios-dependent":[246],"modeling.":[247]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}