{"id":"https://openalex.org/W2962961016","doi":"https://doi.org/10.1109/icassp.2018.8461361","title":"On Modular Training of Neural Acoustics-to-Word Model for LVCSR","display_name":"On Modular Training of Neural Acoustics-to-Word Model for LVCSR","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962961016","doi":"https://doi.org/10.1109/icassp.2018.8461361","mag":"2962961016"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734777","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0003-3067-8333"},"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":"Qi Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348721","display_name":"Hao Li","orcid":"https://orcid.org/0009-0005-4319-9026"},"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":"Hao Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, 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":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4754","last_page":"4758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.8058977127075195},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6977706551551819},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.66108238697052},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5996005535125732},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5448302626609802},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.505366861820221},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4337720572948456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40756574273109436},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2014046013355255},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0948043167591095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058977127075195},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6977706551551819},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.66108238697052},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5996005535125732},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5448302626609802},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.505366861820221},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4337720572948456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40756574273109436},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2014046013355255},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0948043167591095},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/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/icassp.2018.8461361","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461361","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2054910186","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2250539671","https://openalex.org/W2259472270","https://openalex.org/W2293634267","https://openalex.org/W2514741789","https://openalex.org/W2515753980","https://openalex.org/W2520160253","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2548332580","https://openalex.org/W2584407414","https://openalex.org/W2597757402","https://openalex.org/W2741480356","https://openalex.org/W2745439869","https://openalex.org/W2746192915","https://openalex.org/W2748584437","https://openalex.org/W2749514303","https://openalex.org/W2750499125","https://openalex.org/W2888779557","https://openalex.org/W2963158258","https://openalex.org/W2963211739","https://openalex.org/W6629052376","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6692563993","https://openalex.org/W6696934422","https://openalex.org/W6727336983","https://openalex.org/W6728910023","https://openalex.org/W6735390525","https://openalex.org/W6743477263"],"related_works":["https://openalex.org/W2944691285","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/W2125343999","https://openalex.org/W4200200210","https://openalex.org/W2161188302"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"systems":[6],"directly":[7],"map":[8],"acoustics":[9],"to":[10,78,128,150],"words":[11],"using":[12,109,147],"a":[13,23,33,68,103,159],"unified":[14],"model.":[15,170],"Previous":[16],"works":[17],"mostly":[18],"focus":[19],"on":[20,158],"E2E":[21,36,74],"training":[22,37,71,87,175],"single":[24],"model":[25,31,100,105,142],"which":[26],"integrates":[27],"acoustic":[28,50,57,82,110,148],"and":[29,42,55,58,83,102,112,126,144,176],"language":[30,59,84],"into":[32,139],"whole.":[34],"Although":[35],"benefits":[38,179],"from":[39,180],"sequence":[40,130,155],"modeling":[41],"simplified":[43],"decoding":[44,95,119,177],"pipelines,":[45],"large":[46],"amount":[47],"of":[48,73,154],"transcribed":[49],"data":[51,111,114,149],"is":[52,76,122],"usually":[53],"required,":[54],"traditional":[56],"modelling":[60],"techniques":[61],"cannot":[62],"be":[63],"utilized.":[64],"In":[65],"this":[66],"paper,":[67],"novel":[69],"modular":[70],"framework":[72],"ASR":[75],"proposed":[77,182],"separately":[79],"train":[80],"neural":[81],"models":[85],"during":[86],"stage,":[88],"while":[89],"still":[90],"performing":[91],"end-to-end":[92],"inference":[93],"in":[94,173],"stage.":[96],"Here,":[97],"an":[98,140],"acoustics-to-phoneme":[99],"(A2P)":[101],"phoneme-to-word":[104],"(P2W)":[106],"are":[107,137],"trained":[108],"text":[113],"respectively.":[115],"A":[116],"phone":[117],"synchronous":[118],"(PSD)":[120],"module":[121],"inserted":[123],"between":[124],"A2P":[125],"P2W":[127],"reduce":[129],"lengths":[131],"without":[132],"precision":[133],"loss.":[134],"Finally,":[135],"modules":[136],"integrated":[138],"acoustics-to-word":[141],"(A2W)":[143],"jointly":[145],"optimized":[146],"retain":[151],"the":[152,167,181],"advantage":[153],"modeling.":[156],"Experiments":[157],"300-hour":[160],"Switchboard":[161],"task":[162],"show":[163],"significant":[164],"improvement":[165],"over":[166],"direct":[168],"A2W":[169],"The":[171],"efficiency":[172],"both":[174],"also":[178],"method.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}