{"id":"https://openalex.org/W2911726185","doi":"https://doi.org/10.1109/taslp.2019.2894554","title":"Articulatory and Spectrum Information Fusion Based on Deep Recurrent Neural Networks","display_name":"Articulatory and Spectrum Information Fusion Based on Deep Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-01-21","ids":{"openalex":"https://openalex.org/W2911726185","doi":"https://doi.org/10.1109/taslp.2019.2894554","mag":"2911726185"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2019.2894554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2894554","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/A5002510347","display_name":"Jianguo Yu","orcid":"https://orcid.org/0000-0002-7580-4631"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jianguo Yu","raw_affiliation_strings":["Human Interface Lab, University of Aizu, Fukushima, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7580-4631","affiliations":[{"raw_affiliation_string":"Human Interface Lab, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["Human Interface Lab, University of Aizu, Fukushima, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1838-4789","affiliations":[{"raw_affiliation_string":"Human Interface Lab, University of Aizu, Fukushima, Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067714865","display_name":"Tomoko Matsui","orcid":"https://orcid.org/0000-0003-3201-6106"},"institutions":[{"id":"https://openalex.org/I4210134673","display_name":"The Institute of Statistical Mathematics","ror":"https://ror.org/03jcejr58","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I4210134673","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoko Matsui","raw_affiliation_strings":["Department of Statistical Modeling, Institute of Statistical Mathematics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Modeling, Institute of Statistical Mathematics, Tokyo, Japan","institution_ids":["https://openalex.org/I4210134673"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7353,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88341054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"27","issue":"4","first_page":"742","last_page":"752"},"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":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7698482871055603},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7089199423789978},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7012707591056824},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5910459160804749},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5684506893157959},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5612707138061523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48209741711616516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46148768067359924},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4550730288028717},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2876478433609009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698482871055603},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7089199423789978},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7012707591056824},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5910459160804749},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5684506893157959},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5612707138061523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48209741711616516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46148768067359924},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4550730288028717},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2876478433609009},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"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/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/taslp.2019.2894554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2019.2894554","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":0.6899999976158142,"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":58,"referenced_works":["https://openalex.org/W46785905","https://openalex.org/W60202269","https://openalex.org/W175821084","https://openalex.org/W900447646","https://openalex.org/W1447019041","https://openalex.org/W1531883353","https://openalex.org/W1531956331","https://openalex.org/W1564657563","https://openalex.org/W1602122992","https://openalex.org/W1821462560","https://openalex.org/W1883346539","https://openalex.org/W1924770834","https://openalex.org/W1980837758","https://openalex.org/W1982854652","https://openalex.org/W1986174057","https://openalex.org/W2005741747","https://openalex.org/W2011845089","https://openalex.org/W2029996593","https://openalex.org/W2034829178","https://openalex.org/W2052382192","https://openalex.org/W2063036810","https://openalex.org/W2064675550","https://openalex.org/W2091650508","https://openalex.org/W2101802380","https://openalex.org/W2101859041","https://openalex.org/W2105478683","https://openalex.org/W2107878631","https://openalex.org/W2124555689","https://openalex.org/W2125930537","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2148226542","https://openalex.org/W2160815625","https://openalex.org/W2173379916","https://openalex.org/W2253986341","https://openalex.org/W2395955767","https://openalex.org/W2402610474","https://openalex.org/W2555561649","https://openalex.org/W2596135543","https://openalex.org/W2793093816","https://openalex.org/W2962874523","https://openalex.org/W2962946266","https://openalex.org/W4293390340","https://openalex.org/W6601897821","https://openalex.org/W6602447114","https://openalex.org/W6607219637","https://openalex.org/W6628424771","https://openalex.org/W6638523607","https://openalex.org/W6639103823","https://openalex.org/W6640212811","https://openalex.org/W6674963043","https://openalex.org/W6675504311","https://openalex.org/W6678818196","https://openalex.org/W6679030014","https://openalex.org/W6685316698","https://openalex.org/W6711834147","https://openalex.org/W6713398208","https://openalex.org/W6735255722"],"related_works":["https://openalex.org/W2375321655","https://openalex.org/W3128571556","https://openalex.org/W2533508831","https://openalex.org/W2146992157","https://openalex.org/W2546942002","https://openalex.org/W2539985974","https://openalex.org/W2023185280","https://openalex.org/W2374918184","https://openalex.org/W2793122029","https://openalex.org/W2376309785"],"abstract_inverted_index":{"Many":[0],"studies":[1],"have":[2],"shown":[3],"that":[4,77,215],"articulatory":[5,51,64,94,135,183],"features":[6,19,52,201,237],"can":[7],"significantly":[8],"improve":[9],"the":[10,38,45,49,56,69,108,116,131,134,139,155,160,166,180,195,211,217,230],"performance":[11,225],"of":[12,42,102,150],"automatic":[13],"speech":[14,57],"recognition":[15,24,79,99],"systems.":[16],"Unfortunately,":[17],"such":[18],"are":[20,27,53,143,189],"not":[21],"available":[22],"at":[23],"time.":[25],"There":[26],"two":[28,89],"main":[29],"approaches":[30],"to":[31,92,164,223,229],"solve":[32],"this":[33,85,170],"problem:":[34],"a":[35,60,75,97,122,147,173],"feature-based":[36,132],"approach,":[37,62],"most":[39],"popular":[40],"example":[41],"which":[43],"is":[44,66,104,110,121,176],"acoustic-to-articulatory":[46],"inversion,":[47],"where":[48,63],"missing":[50],"generated":[54],"from":[55,210],"signal,":[58],"and":[59,72,107,138,182,185],"model-based":[61,156],"information":[65,95],"embedded":[67],"in":[68,74],"model":[70,111,119,127,141,233],"structure":[71],"parameters":[73],"way":[76],"allows":[78],"using":[80,146,207],"only":[81],"acoustic":[82,118,140,181,200,232,236],"features.":[83],"In":[84,113,130,154,169],"paper,":[86],"we":[87,158],"propose":[88],"new":[90],"methods":[91,219],"integrate":[93],"into":[96],"phoneme":[98],"system.":[100],"One":[101],"them":[103],"feature":[105],"based,":[106],"other":[109],"based.":[112],"both":[114,179,216],"cases,":[115],"underlying":[117],"(AM)":[120],"deep":[123],"neural":[124],"networks-hidden":[125],"Markov":[126],"(DNN-HMM)":[128],"hybrid.":[129],"method,":[133,157],"inversion":[136],"DNN":[137,142,175,197,231],"trained":[144,177,234],"jointly":[145],"linear":[148],"combination":[149],"their":[151],"loss":[152],"functions.":[153],"utilize":[159],"generalized":[161],"distillation":[162],"framework":[163],"train":[165],"AM":[167,196],"DNN.":[168],"case,":[171],"first,":[172],"teacher":[174],"on":[178],"features,":[184],"then":[186],"its":[187],"outputs":[188],"used":[190],"as":[191],"additional":[192],"targets":[193],"during":[194],"training":[198],"with":[199,227,235],"only.":[202,238],"A":[203],"7-fold":[204],"cross-validation":[205],"experiments":[206],"42":[208],"speakers":[209],"XRMB":[212],"database":[213],"showed":[214],"proposed":[218],"provide":[220],"about":[221],"22%":[222],"25%":[224],"improvement":[226],"respect":[228]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}