{"id":"https://openalex.org/W4254365061","doi":"https://doi.org/10.1109/iscslp.2016.7918420","title":"CTC regularized model adaptation for improving LSTM RNN based multi-accent Mandarin speech recognition","display_name":"CTC regularized model adaptation for improving LSTM RNN based multi-accent Mandarin speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W4254365061","doi":"https://doi.org/10.1109/iscslp.2016.7918420"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"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":"Jiangyan Yi","raw_affiliation_strings":["School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029516423","display_name":"Hao Ni","orcid":"https://orcid.org/0000-0001-5485-4376"},"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":"Hao Ni","raw_affiliation_strings":["School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattem Recognition, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattem Recognition, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395562","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0003-1529-1552"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["National Laboratory of Pattem Recognition, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattem Recognition, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"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":"Jianhua Tao","raw_affiliation_strings":["School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9933000206947327,"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":0.9904999732971191,"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":0.8000974655151367},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7844206690788269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.733497679233551},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6697359681129456},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5773012638092041},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5674832463264465},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5661928057670593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551476776599884},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5443451404571533},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43883922696113586},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43180787563323975},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3624579906463623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000974655151367},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7844206690788269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.733497679233551},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6697359681129456},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5773012638092041},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5674832463264465},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5661928057670593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551476776599884},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5443451404571533},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43883922696113586},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43180787563323975},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3624579906463623},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/iscslp.2016.7918420","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W5524598","https://openalex.org/W143647774","https://openalex.org/W184039015","https://openalex.org/W1499864241","https://openalex.org/W1978986151","https://openalex.org/W1989549063","https://openalex.org/W2025198378","https://openalex.org/W2094975628","https://openalex.org/W2101066392","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2160815625","https://openalex.org/W2169883442","https://openalex.org/W2294108103","https://openalex.org/W2399843513","https://openalex.org/W2400607496","https://openalex.org/W2405866807","https://openalex.org/W2406264770","https://openalex.org/W2963211739","https://openalex.org/W6600211438","https://openalex.org/W6605885551","https://openalex.org/W6607605394","https://openalex.org/W6629930100","https://openalex.org/W6645118814","https://openalex.org/W6684803408","https://openalex.org/W6696757691","https://openalex.org/W6713969595"],"related_works":["https://openalex.org/W2021413527","https://openalex.org/W1539047115","https://openalex.org/W1664345252","https://openalex.org/W2963920996","https://openalex.org/W1489125746","https://openalex.org/W4297665160","https://openalex.org/W1516378513","https://openalex.org/W2141731574","https://openalex.org/W1533416326","https://openalex.org/W2972686346"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,48,64],"novel":[4],"regularized":[5],"adaptation":[6,50,120],"method":[7,135],"for":[8],"long":[9],"short":[10],"term":[11,66],"memory":[12],"(LSTM)":[13],"recurrent":[14],"neural":[15],"network":[16,45],"(RNN)":[17],"based":[18],"acoustic":[19],"model":[20,88],"trained":[21],"with":[22,47,141],"connectionist":[23],"temporal":[24],"classification":[25],"(CTC)":[26],"loss":[27],"function":[28],"(LSTM-RNN-CTC)":[29],"to":[30,54,58,67,89,92,115],"improve":[31],"the":[32,44,68,74,86,93,110,133],"performance":[33],"of":[34,101],"multi-accent":[35],"Mandarin":[36],"speech":[37,129],"recognition":[38],"task.":[39],"In":[40,56],"general,":[41],"directly":[42],"adjusting":[43],"parameters":[46],"small":[49],"set":[51],"may":[52],"lead":[53],"over-fitting.":[55],"order":[57],"avoid":[59],"this":[60,119],"problem,":[61],"we":[62],"add":[63],"regularization":[65],"original":[69],"training":[70],"criterion.":[71],"It":[72],"forces":[73],"conditional":[75],"probability":[76],"distribution":[77],"over":[78],"initial":[79],"and":[80,125],"final":[81],"(I/F)":[82],"sequences":[83],"estimated":[84],"from":[85],"adapted":[87],"be":[90,106,116],"close":[91],"accent":[94,128],"independent":[95],"(AI)":[96],"model.":[97,144],"Meanwhile,":[98],"hidden":[99],"layers":[100],"LSTM":[102],"RNN":[103],"should":[104],"not":[105],"adjusted,":[107],"but":[108],"only":[109],"accent-specific":[111],"output":[112],"layer":[113],"needs":[114],"fine-tuned":[117],"using":[118],"method.":[121],"Experiments":[122],"on":[123],"RASC863":[124],"CASIA":[126],"regional":[127],"corpus":[130],"show":[131],"that":[132],"proposed":[134],"obtains":[136],"obvious":[137],"improvement":[138],"when":[139],"compared":[140],"LSTM-RNN-CTC":[142],"baseline":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}