{"id":"https://openalex.org/W4402111563","doi":"https://doi.org/10.21437/interspeech.2024-1269","title":"Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator","display_name":"Speaker-Independent Acoustic-to-Articulatory Inversion through Multi-Channel Attention Discriminator","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111563","doi":"https://doi.org/10.21437/interspeech.2024-1269"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1269","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1269","pdf_url":"https://www.isca-archive.org/interspeech_2024/chung24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/chung24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103237158","display_name":"Woojin Chung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Woo-Jin Chung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5557,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71467521,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1540","last_page":"1544"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8866999745368958,"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":0.8866999745368958,"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":0.8669000267982483,"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/discriminator","display_name":"Discriminator","score":0.899600625038147},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.611910879611969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6011011004447937},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5799345970153809},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4872845411300659},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.45263397693634033},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.20373693108558655},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20151981711387634},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08849877119064331}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.899600625038147},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.611910879611969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6011011004447937},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5799345970153809},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4872845411300659},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.45263397693634033},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.20373693108558655},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20151981711387634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08849877119064331},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1269","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1269","pdf_url":"https://www.isca-archive.org/interspeech_2024/chung24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1269","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1269","pdf_url":"https://www.isca-archive.org/interspeech_2024/chung24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111563.pdf","grobid_xml":"https://content.openalex.org/works/W4402111563.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W2387995142","https://openalex.org/W4380714744","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2057775761","https://openalex.org/W2964074194","https://openalex.org/W2800597160"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,33,87],"novel":[3],"speaker-independent":[4,97],"acoustic-toarticulatory":[5],"inversion":[6],"(AAI)":[7],"model,":[8],"overcoming":[9],"the":[10,43,56,78],"limitations":[11],"observed":[12],"in":[13,50,96],"conventional":[14],"AAI":[15,57,98],"models":[16],"that":[17],"rely":[18],"on":[19],"acoustic":[20],"features":[21],"derived":[22],"from":[23,32],"restricted":[24],"datasets.To":[25],"address":[26],"these":[27],"challenges,":[28],"we":[29],"leverage":[30],"representations":[31],"pre-trained":[34],"selfsupervised":[35],"learning":[36],"(SSL)":[37],"model":[38,61],"to":[39,75],"more":[40],"effectively":[41],"estimate":[42],"global,":[44],"local,":[45],"and":[46,66,102],"kinematic":[47],"pattern":[48],"information":[49],"Electromagnetic":[51],"Articulography":[52],"(EMA)":[53],"signals":[54],"during":[55],"process.We":[58],"train":[59],"our":[60],"using":[62],"an":[63,68],"adversarial":[64],"approach":[65],"introduce":[67],"attention-based":[69],"Multi-duration":[70],"phoneme":[71],"discriminator":[72],"(MDPD)":[73],"designed":[74],"fully":[76],"capture":[77],"intricate":[79],"relationship":[80],"among":[81],"multi-channel":[82],"articulatory":[83],"signals.Our":[84],"method":[85],"achieves":[86],"Pearson":[88],"correlation":[89],"coefficient":[90],"of":[91],"0.847,":[92],"marking":[93],"state-of-theart":[94],"performance":[95],"models.The":[99],"implementation":[100],"details":[101],"code":[103],"can":[104],"be":[105],"found":[106],"online":[107],"1":[108],".":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}