{"id":"https://openalex.org/W2610986383","doi":"https://doi.org/10.1109/iscslp.2016.7918372","title":"Applying connectionist temporal classification objective function to Chinese Mandarin speech recognition","display_name":"Applying connectionist temporal classification objective function to Chinese Mandarin speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2610986383","doi":"https://doi.org/10.1109/iscslp.2016.7918372","mag":"2610986383"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918372","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":"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/A5103095739","display_name":"Pengrui Wang","orcid":"https://orcid.org/0009-0007-9325-9693"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengrui Wang","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, China, P.R. China"],"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, China, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028530320","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-7075-4145"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, China, P.R. China"],"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, China, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]},{"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":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, China, P.R. China"],"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, China, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103095739"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13001296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9962000250816345,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9911999702453613,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8655006289482117},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7492741346359253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7415051460266113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7406615614891052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5299554467201233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5184630751609802},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4402908682823181},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2662430703639984},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19545578956604004}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8655006289482117},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7492741346359253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7415051460266113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7406615614891052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299554467201233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5184630751609802},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4402908682823181},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2662430703639984},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19545578956604004},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918372","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":[{"display_name":"Quality Education","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1492459858","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1533416326","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2046932483","https://openalex.org/W2102113734","https://openalex.org/W2119615570","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2147768505","https://openalex.org/W2193413348","https://openalex.org/W2293634267","https://openalex.org/W2395416438","https://openalex.org/W2397569915","https://openalex.org/W2898360541","https://openalex.org/W2963211739","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6696934422","https://openalex.org/W6713047518","https://openalex.org/W6755964870"],"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":{"In":[0],"automatic":[1],"speech":[2,80],"recognition":[3,81],"(ASR),":[4],"connectionist":[5],"temporal":[6],"classification":[7],"(CTC)":[8],"is":[9],"regarded":[10],"as":[11,37],"a":[12,99,104,133],"method":[13],"to":[14],"achieve":[15],"end-to-end":[16,101],"system.":[17],"Actually,":[18],"not":[19],"only":[20],"characters":[21],"(Chars)":[22],"but":[23],"also":[24],"context":[25,30],"independent":[26],"phonemes":[27],"(CI-Phns)":[28],"or":[29],"dependent":[31],"phoneme":[32],"(CD-Phns)":[33],"can":[34],"be":[35,75],"used":[36],"output":[38],"units":[39,62],"of":[40,46,109],"CTC-trained":[41,71,94],"neural":[42],"network.":[43],"The":[44,70],"contribution":[45],"this":[47],"paper":[48],"mainly":[49],"lies":[50],"in":[51],"three":[52,60],"aspects:":[53],"First,":[54],"we":[55,84,131],"trained":[56],"CTC":[57],"models":[58],"with":[59,143,151],"different":[61],"(Char,":[63],"CI-Phn":[64],"and":[65,88],"CD-Phn)":[66],"on":[67,78,111],"Chinese":[68],"Mandarin.":[69],"CD-Phn":[72,124],"model":[73,125],"might":[74],"first":[76],"realized":[77],"Mandarin":[79],"(SR).":[82],"Second,":[83],"optimize":[85],"the":[86,116],"training":[87],"decoding":[89],"procedures,":[90],"which":[91,114,147],"benefit":[92],"our":[93,123,127,152],"models.":[95],"Our":[96],"Char":[97],"model,":[98],"real":[100],"system,":[102],"achieves":[103,148],"character":[105],"error":[106],"rate":[107],"(CER)":[108],"34.22%":[110],"HKUST":[112],"corpus":[113],"surpasses":[115],"result":[117],"(39.70%)":[118],"reported":[119],"by":[120],"EESEN.":[121],"Additionally,":[122],"outperforms":[126],"hybrid":[128],"model.":[129],"Finally,":[130],"build":[132],"CTC-based":[134],"online":[135],"system":[136],"using":[137],"unidirectional":[138],"Long":[139],"Short-term":[140],"Memory":[141],"(UniLSTM)":[142],"row":[144],"convolution":[145],"(RC),":[146],"comparable":[149],"performance":[150],"bidirectional":[153],"LSTM":[154],"(BiLSTM).":[155]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}