{"id":"https://openalex.org/W4372260274","doi":"https://doi.org/10.1109/icassp49357.2023.10096401","title":"Articulatory Representation Learning via Joint Factor Analysis and Neural Matrix Factorization","display_name":"Articulatory Representation Learning via Joint Factor Analysis and Neural Matrix Factorization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260274","doi":"https://doi.org/10.1109/icassp49357.2023.10096401"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5038985725","display_name":"Jiachen Lian","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiachen Lian","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan W Black","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030851305","display_name":"Yijing Lu","orcid":"https://orcid.org/0000-0001-8365-4277"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijing Lu","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110122617","display_name":"Louis Goldstein","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis Goldstein","raw_affiliation_strings":["University of Southern California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala K. Anumanchipalli","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038985725"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":1.7346,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84162276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7449829578399658},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6432117819786072},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6377542018890381},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6005532741546631},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5546959042549133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5442110300064087},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5269770622253418},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49950385093688965},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.4680846333503723},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4468006491661072},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4288555979728699},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.41731810569763184},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.4139372408390045},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.08749008178710938}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449829578399658},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6432117819786072},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6377542018890381},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6005532741546631},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5546959042549133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5442110300064087},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5269770622253418},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49950385093688965},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.4680846333503723},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4468006491661072},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4288555979728699},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.41731810569763184},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.4139372408390045},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.08749008178710938},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096401","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W123135133","https://openalex.org/W1522301498","https://openalex.org/W2046681189","https://openalex.org/W2048449762","https://openalex.org/W2068447135","https://openalex.org/W2113413162","https://openalex.org/W2118718620","https://openalex.org/W2127141656","https://openalex.org/W2158203944","https://openalex.org/W2614575902","https://openalex.org/W2747874407","https://openalex.org/W2930178207","https://openalex.org/W2972818416","https://openalex.org/W2998249245","https://openalex.org/W3007328579","https://openalex.org/W3209984917","https://openalex.org/W4206319965","https://openalex.org/W4213171936","https://openalex.org/W4223430326","https://openalex.org/W4280552695","https://openalex.org/W4281492411","https://openalex.org/W4281743943","https://openalex.org/W6631190155","https://openalex.org/W6677759377","https://openalex.org/W6772230580","https://openalex.org/W6838853235"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840"],"abstract_inverted_index":{"Articulatory":[0],"representation":[1,114],"learning":[2],"is":[3,94,139],"the":[4,23,32,65,72,82,101,119,127,143,148,157,162,175,180],"fundamental":[5],"research":[6],"in":[7,64],"modeling":[8],"neural":[9,134],"speech":[10,40],"production":[11,41],"system.":[12],"Our":[13],"previous":[14],"work":[15,53],"has":[16],"established":[17],"a":[18,111],"deep":[19],"paradigm":[20],"to":[21,125,146],"decompose":[22],"articulatory":[24,113,181],"kinematics":[25],"data":[26,93],"into":[27],"gestures,":[28],"which":[29,80,99],"explicitly":[30],"model":[31],"phonological":[33],"and":[34,43,87,130,151,169,188],"linguistic":[35],"structure":[36],"encoded":[37],"with":[38,49,156],"human":[39],"mechanism,":[42],"corresponding":[44],"gestural":[45,88,152],"scores.":[46,132,153],"We":[47,154],"continue":[48],"this":[50,107],"line":[51],"of":[52,71,84,103,121],"by":[54],"raising":[55],"two":[56],"concerns:":[57],"(1)":[58],"The":[59,91],"articulators":[60,73],"are":[61,184],"entangled":[62],"together":[63],"original":[66],"algorithm":[67,116,138],"such":[68],"that":[69,117,160,174,183],"some":[70],"do":[74],"not":[75],"leverage":[76],"effective":[77],"moving":[78],"patterns,":[79],"limits":[81,100],"interpretability":[83],"both":[85],"gestures":[86,150],"scores;":[89],"(2)":[90],"EMA":[92],"sparsely":[95],"sampled":[96],"from":[97],"articulators,":[98],"intelligibility":[102],"learned":[104],"representations.":[105],"In":[106],"work,":[108],"we":[109],"propose":[110],"novel":[112],"decomposition":[115],"takes":[118],"advantage":[120],"guided":[122],"factor":[123,131,144],"analysis":[124],"derive":[126,147],"articulatory-specific":[128],"factors":[129],"A":[133],"convolutive":[135],"matrix":[136],"factorization":[137],"then":[140],"employed":[141],"on":[142],"scores":[145],"new":[149],"experiment":[155],"rtMRI":[158],"corpus":[159],"captures":[161],"fine-grained":[163],"vocal":[164],"tract":[165],"contours.":[166],"Both":[167],"subjective":[168],"objective":[170],"evaluation":[171],"results":[172],"suggest":[173],"newly":[176],"proposed":[177],"system":[178],"delivers":[179],"representations":[182],"intelligible,":[185],"generalizable,":[186],"efficient":[187],"interpretable.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}