{"id":"https://openalex.org/W4416798393","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249146","title":"A Dual-Path Speaker-Independent Acoustic-Toarticulatory Inversion Model Based on Content and Speaker Information Disentanglement","display_name":"A Dual-Path Speaker-Independent Acoustic-Toarticulatory Inversion Model Based on Content and Speaker Information Disentanglement","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798393","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249146"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5101779069","display_name":"Qiang Fang","orcid":"https://orcid.org/0000-0002-6548-980X"},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiang Fang","raw_affiliation_strings":["Institute of Linguistics, Chinese Academy of Social Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Linguistics, Chinese Academy of Social Sciences","institution_ids":["https://openalex.org/I114218197"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101779069"],"corresponding_institution_ids":["https://openalex.org/I114218197"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19436779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"712","last_page":"717"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.36169999837875366,"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":0.36169999837875366,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.3190999925136566,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.14219999313354492,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7109000086784363},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6876000165939331},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4848000109195709},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.47690001130104065},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4156999886035919}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7109000086784363},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6876000165939331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.657800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609000027179718},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C71907059","wikidata":"https://www.wikidata.org/wiki/Q223323","display_name":"Root mean square","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.367900013923645},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3149999976158142},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2988709989","wikidata":"https://www.wikidata.org/wiki/Q85784623","display_name":"Mean square","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C11577676","wikidata":"https://www.wikidata.org/wiki/Q134237","display_name":"Square root","level":2,"score":0.2921000123023987}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4716616089","display_name":null,"funder_award_id":"61977049","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W40881502","https://openalex.org/W157899740","https://openalex.org/W201148316","https://openalex.org/W1973016470","https://openalex.org/W1982854652","https://openalex.org/W1990394889","https://openalex.org/W2002620567","https://openalex.org/W2006775235","https://openalex.org/W2034829178","https://openalex.org/W2069618035","https://openalex.org/W2395955767","https://openalex.org/W2402610474","https://openalex.org/W2460967393","https://openalex.org/W2622158094","https://openalex.org/W2963464520","https://openalex.org/W2972659941","https://openalex.org/W3095756896","https://openalex.org/W4224918482","https://openalex.org/W4372340876","https://openalex.org/W4375868835","https://openalex.org/W4402111563"],"related_works":[],"abstract_inverted_index":{"Speaker-independent":[0],"acoustic-to-articulatory":[1],"inversion":[2],"(AAI)":[3],"is":[4,20,61,122],"a":[5,45,85],"technique":[6],"for":[7,16,24],"estimating":[8],"articulatory":[9,78,90],"trajectories":[10],"from":[11,35],"input":[12,59,132],"acoustic":[13],"speech":[14,60],"signals":[15],"unseen":[17],"speakers.":[18],"This":[19],"of":[21,71,88,104,109,126],"great":[22],"importance":[23],"several":[25],"theoretical":[26],"and":[27,30,65,81],"practical":[28],"issues":[29],"has":[31],"attracted":[32],"increasing":[33],"attention":[34],"researchers":[36],"in":[37,107],"recent":[38],"years.":[39],"In":[40,54],"this":[41,52],"study,":[42],"we":[43],"propose":[44],"dual-path":[46],"speaker-independent":[47,105],"AAI":[48,106],"model":[49],"to":[50,76,124],"address":[51],"issue.":[53],"the":[55,58,77,97,102,110,117,127],"proposed":[56,98],"model,":[57],"decomposed":[62],"into":[63],"speaker":[64],"content":[66],"embeddings.":[67],"These":[68],"two":[69],"types":[70],"embeddings":[72],"are":[73],"independently":[74],"inverted":[75],"counter":[79],"parts":[80],"then":[82],"fused":[83],"through":[84],"pretrained":[86],"decoder":[87],"an":[89],"variational":[91],"autoencoder.":[92],"The":[93],"results":[94],"indicate":[95],"that":[96,125],"approach":[99,129],"significantly":[100],"improves":[101],"performance":[103],"terms":[108],"root":[111],"mean":[112],"square":[113],"error":[114],"(RMSE),":[115],"while":[116],"Pearson":[118],"correlation":[119],"coefficient":[120],"(PCC)":[121],"comparable":[123],"state-of-art":[128],"with":[130],"MFCC":[131],"only.":[133]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}