{"id":"https://openalex.org/W4372340876","doi":"https://doi.org/10.1109/icassp49357.2023.10096796","title":"Speaker-Independent Acoustic-to-Articulatory Speech Inversion","display_name":"Speaker-Independent Acoustic-to-Articulatory Speech Inversion","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372340876","doi":"https://doi.org/10.1109/icassp49357.2023.10096796"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096796","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/A5081837203","display_name":"Peter Wu","orcid":"https://orcid.org/0000-0001-6503-3936"},"institutions":[{"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":"Peter Wu","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"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":"Li-Wei Chen","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/A5015390421","display_name":"Cheol Jun Cho","orcid":null},"institutions":[{"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":"Cheol Jun Cho","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"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":"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/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":"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/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":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5081837203"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.8887,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92459249,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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/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/T10403","display_name":"Phonetics and Phonology Research","score":0.9998000264167786,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7313283085823059},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.7268730401992798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215608358383179},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6380929946899414},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6091938614845276},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5057525634765625},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44612330198287964},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4284050464630127},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.42413222789764404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.402234822511673},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3383179306983948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1744123101234436},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14951053261756897}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7313283085823059},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.7268730401992798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215608358383179},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6380929946899414},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6091938614845276},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5057525634765625},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44612330198287964},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4284050464630127},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.42413222789764404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.402234822511673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3383179306983948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1744123101234436},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14951053261756897},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C204723758","wikidata":"https://www.wikidata.org/wiki/Q3882459","display_name":"Acoustic wave","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096796","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W46785905","https://openalex.org/W95152782","https://openalex.org/W1567811979","https://openalex.org/W1924770834","https://openalex.org/W1945090009","https://openalex.org/W2027933203","https://openalex.org/W2068447135","https://openalex.org/W2231075402","https://openalex.org/W2395955767","https://openalex.org/W2524541983","https://openalex.org/W2622158094","https://openalex.org/W2747874407","https://openalex.org/W2753709519","https://openalex.org/W2766736793","https://openalex.org/W2804300206","https://openalex.org/W2940585064","https://openalex.org/W2962780374","https://openalex.org/W2972359262","https://openalex.org/W2972916618","https://openalex.org/W2988842707","https://openalex.org/W3092028330","https://openalex.org/W3140429000","https://openalex.org/W3160719719","https://openalex.org/W3163341344","https://openalex.org/W3167533889","https://openalex.org/W3197192693","https://openalex.org/W3197580070","https://openalex.org/W3198878417","https://openalex.org/W3202658488","https://openalex.org/W3206375275","https://openalex.org/W3208546454","https://openalex.org/W3209059054","https://openalex.org/W4206087508","https://openalex.org/W4221109856","https://openalex.org/W4224918482","https://openalex.org/W4235733905","https://openalex.org/W4286899907","https://openalex.org/W4297841322","https://openalex.org/W4297841848","https://openalex.org/W4301371414","https://openalex.org/W6603838645","https://openalex.org/W6640212811","https://openalex.org/W6640608080","https://openalex.org/W6783867762","https://openalex.org/W6791823829","https://openalex.org/W6802489979","https://openalex.org/W6802659129","https://openalex.org/W6802838302","https://openalex.org/W6803547063"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2766824185","https://openalex.org/W266498968","https://openalex.org/W1967798504","https://openalex.org/W4372340876"],"abstract_inverted_index":{"To":[0,46],"build":[1,50],"speech":[2,8,24,44,102],"processing":[3],"methods":[4],"that":[5,56,113],"can":[6],"handle":[7],"as":[9,11],"naturally":[10],"humans,":[12],"researchers":[13],"have":[14],"explored":[15],"multiple":[16],"ways":[17],"of":[18,43,90,98],"building":[19],"an":[20,26,51,75,124],"invertible":[21],"mapping":[22],"from":[23],"to":[25,64,66],"interpretable":[27],"space.":[28],"The":[29],"articulatory":[30,118],"space":[31,39],"is":[32],"a":[33,108],"promising":[34],"inversion":[35,53],"target,":[36],"since":[37],"this":[38,47],"captures":[40],"the":[41,81,88,96],"mechanics":[42],"production.":[45],"end,":[48],"we":[49,86,106],"acoustic-to-articulatory":[52],"(AAI)":[54],"model":[55],"leverages":[57],"autoregression,":[58],"adversarial":[59],"training,":[60],"and":[61],"self":[62],"supervision":[63],"generalize":[65],"unseen":[67],"speakers.":[68],"Our":[69],"approach":[70],"obtains":[71],"0.784":[72],"correlation":[73],"on":[74,117],"electromagnetic":[76],"articulography":[77],"(EMA)":[78],"dataset,":[79],"improving":[80],"state-of-the-art":[82],"by":[83],"12.5%.":[84],"Additionally,":[85],"show":[87],"interpretability":[89],"these":[91],"representations":[92,100],"through":[93],"directly":[94],"com-paring":[95],"behavior":[97],"estimated":[99],"with":[101,123],"production":[103],"behavior.":[104],"Finally,":[105],"propose":[107],"resynthesis-based":[109],"AAI":[110],"evaluation":[111],"metric":[112],"does":[114],"not":[115],"rely":[116],"labels,":[119],"demonstrating":[120],"its":[121],"efficacy":[122],"18-speaker":[125],"dataset.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
