{"id":"https://openalex.org/W2548332580","doi":"https://doi.org/10.1109/taslp.2016.2625459","title":"Phone Synchronous Speech Recognition With CTC Lattices","display_name":"Phone Synchronous Speech Recognition With CTC Lattices","publication_year":2016,"publication_date":"2016-11-04","ids":{"openalex":"https://openalex.org/W2548332580","doi":"https://doi.org/10.1109/taslp.2016.2625459","mag":"2548332580"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2625459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2625459","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001130005","display_name":"Yimeng Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimeng Zhuang","raw_affiliation_strings":["Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002433660"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":8.998,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.97865526,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"25","issue":"1","first_page":"90","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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":0.8531473875045776},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7624161243438721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6854826807975769},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.6843764781951904},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5345066785812378},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.5047138929367065},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.489096462726593},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4770630896091461},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45623043179512024},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.4540258049964905},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.441129595041275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4022409915924072},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.38587647676467896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3663734197616577},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.2611857056617737},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18556535243988037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8531473875045776},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7624161243438721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6854826807975769},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.6843764781951904},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5345066785812378},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.5047138929367065},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.489096462726593},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4770630896091461},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45623043179512024},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.4540258049964905},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.441129595041275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4022409915924072},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.38587647676467896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3663734197616577},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.2611857056617737},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18556535243988037},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2625459","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2625459","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2368558818","display_name":null,"funder_award_id":"61603252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5039175848","display_name":null,"funder_award_id":"61573241","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"},{"id":"https://openalex.org/F4320336023","display_name":"Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W4495056","https://openalex.org/W27187656","https://openalex.org/W158407117","https://openalex.org/W1499864241","https://openalex.org/W1508165687","https://openalex.org/W1515156256","https://openalex.org/W1534536260","https://openalex.org/W1578856370","https://openalex.org/W1631260214","https://openalex.org/W1734538896","https://openalex.org/W1846543939","https://openalex.org/W1984446451","https://openalex.org/W1985268941","https://openalex.org/W1999488431","https://openalex.org/W2008927795","https://openalex.org/W2010291496","https://openalex.org/W2026149468","https://openalex.org/W2034940213","https://openalex.org/W2040226630","https://openalex.org/W2046932483","https://openalex.org/W2087382212","https://openalex.org/W2113411173","https://openalex.org/W2115008841","https://openalex.org/W2115035712","https://openalex.org/W2117821589","https://openalex.org/W2118835780","https://openalex.org/W2122028591","https://openalex.org/W2124261772","https://openalex.org/W2127099688","https://openalex.org/W2127141656","https://openalex.org/W2134587001","https://openalex.org/W2136727248","https://openalex.org/W2138889249","https://openalex.org/W2142384583","https://openalex.org/W2142532986","https://openalex.org/W2155427043","https://openalex.org/W2156561020","https://openalex.org/W2163139469","https://openalex.org/W2171928131","https://openalex.org/W2193413348","https://openalex.org/W2291513470","https://openalex.org/W2293829681","https://openalex.org/W2293997542","https://openalex.org/W2345190899","https://openalex.org/W2395294869","https://openalex.org/W2395416438","https://openalex.org/W2396384435","https://openalex.org/W2408623794","https://openalex.org/W2507132449","https://openalex.org/W2510945575","https://openalex.org/W2514741789","https://openalex.org/W2612891210","https://openalex.org/W2949640717","https://openalex.org/W2963211739","https://openalex.org/W2963920996","https://openalex.org/W4300671642","https://openalex.org/W6600187464","https://openalex.org/W6601066586","https://openalex.org/W6606465599","https://openalex.org/W6608351678","https://openalex.org/W6629930100","https://openalex.org/W6636811518","https://openalex.org/W6678619499","https://openalex.org/W6687566353","https://openalex.org/W6697286547","https://openalex.org/W6712409652"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2133857928","https://openalex.org/W2143297499","https://openalex.org/W2535886977","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905","https://openalex.org/W1843778016"],"abstract_inverted_index":{"Connectionist":[0],"temporal":[1],"classification":[2],"(CTC)":[3],"has":[4],"recently":[5],"shown":[6],"improved":[7],"performance":[8,167],"and":[9,33,66,126,142,204],"efficiency":[10],"in":[11,103,150],"automatic":[12],"speech":[13,129,139],"recognition.":[14],"One":[15],"popular":[16],"decoding":[17,52,88,158],"implementation":[18],"is":[19,45,63,68,90],"to":[20,25,98,112,170],"use":[21],"a":[22,40,84],"CTC":[23,62,120,123,177,186],"model":[24,202],"predict":[26],"the":[27,48,57,200,206],"phone":[28,86,156],"posteriors":[29],"at":[30],"each":[31],"frame":[32,50,171],"then":[34],"perform":[35],"Viterbi":[36],"beam":[37],"search":[38,78,95,105,163,207],"on":[39,81],"modified":[41],"WFST":[42],"network.":[43],"This":[44],"still":[46],"within":[47],"traditional":[49],"synchronous":[51,87,157,172],"framework.":[53],"In":[54],"this":[55,82,151],"paper,":[56],"peaky":[58],"posterior":[59],"property":[60],"of":[61],"carefully":[64],"investigated":[65],"it":[67],"found":[69],"that":[70,155],"ignoring":[71],"blank":[72,99],"frames":[73],"will":[74],"not":[75,188],"introduce":[76],"additional":[77],"errors.":[79],"Based":[80],"phenomenon,":[83],"novel":[85],"framework":[89,109],"proposed":[91,149],"by":[92],"removing":[93],"tremendous":[94],"redundancy":[96],"due":[97],"frames,":[100],"which":[101],"results":[102],"significant":[104,191],"speed":[106,164],"up.":[107],"The":[108],"naturally":[110],"leads":[111],"an":[113],"extremely":[114],"compact":[115],"phone-level":[116],"acoustic":[117],"space":[118],"representation:":[119],"lattice.":[121],"With":[122],"lattice,":[124],"efficient":[125],"effective":[127],"modular":[128],"recognition":[130,140],"approaches,":[131],"second":[132],"pass":[133],"rescoring":[134],"for":[135],"large":[136],"vocabulary":[137],"continuous":[138],"(LVCSR),":[141],"phone-based":[143],"keyword":[144],"spotting":[145],"(KWS),":[146],"are":[147],"also":[148,197],"paper.":[152],"Experiments":[153],"showed":[154],"can":[159,179],"achieve":[160,180],"3-4":[161],"times":[162],"up":[165],"without":[166],"degradation":[168],"compared":[169],"decoding.":[173],"Modular":[174],"LVCSR":[175],"with":[176,185],"lattice":[178,187],"further":[181],"WER":[182],"improvement.":[183],"KWS":[184,201],"only":[189],"achieved":[190],"equal":[192],"error":[193],"rate":[194],"improvement,":[195],"but":[196],"greatly":[198],"reduced":[199],"size":[203],"increased":[205],"speed.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}