{"id":"https://openalex.org/W4402111720","doi":"https://doi.org/10.21437/interspeech.2024-1740","title":"Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion","display_name":"Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111720","doi":"https://doi.org/10.21437/interspeech.2024-1740"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1740","pdf_url":null,"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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113348443","display_name":"Yun Hao","orcid":"https://orcid.org/0000-0002-2873-8571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912596","display_name":"Reihaneh Amooie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reihaneh Amooie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051972245","display_name":"Wietse de Vries","orcid":"https://orcid.org/0000-0002-0433-090X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wietse de Vries","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072662247","display_name":"Thomas Tienkamp","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Tienkamp","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044408832","display_name":"Rik van Noord","orcid":"https://orcid.org/0000-0002-2666-7466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rik van Noord","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075698724","display_name":"Martijn Wieling","orcid":"https://orcid.org/0000-0003-0434-1526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martijn Wieling","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13017016,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4603","last_page":"4607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9763000011444092,"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":0.9763000011444092,"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":0.9110999703407288,"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":0.7107127904891968},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6980812549591064},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6064210534095764},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44247862696647644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40406256914138794},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05298715829849243}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107127904891968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6980812549591064},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6064210534095764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44247862696647644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40406256914138794},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05298715829849243},{"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-1740","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hao, Y, Amooie, R, de Vries, W, Tienkamp, T, van Noord, R & Wieling, M 2024, Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion. in Proceedings of Interspeech 2024. ISCA, pp. 4603-4607, Interspeech 2024, Kos, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1740","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:publications/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hao, Y, Amooie, R, de Vries, W, Tienkamp, T, van Noord, R & Wieling, M 2024, Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion. in Proceedings of Interspeech 2024. ISCA, pp. 4603-4607, Interspeech 2024, Kos, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1740","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/586bb6f3-8a56-4f27-b5bf-f2a0c8f2b925","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hao, Y, Amooie, R, de Vries, W, Tienkamp, T, van Noord, R & Wieling, M 2024, Exploring Self-Supervised Speech Representations for Cross-lingual Acoustic-to-Articulatory Inversion. in Proceedings of Interspeech 2024. ISCA, pp. 4603-4607, Interspeech 2024, Kos, Greece, 01/09/2024. https://doi.org/10.21437/Interspeech.2024-1740","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Acoustic-to-articulatory":[0],"inversion":[1],"(AAI)":[2],"is":[3,27],"the":[4,31,83],"process":[5],"of":[6,33],"inferring":[7],"vocal":[8],"tract":[9],"movements":[10],"from":[11],"acoustic":[12],"speech":[13],"signals.":[14],"Despite":[15],"its":[16],"diverse":[17],"potential":[18,48],"applications,":[19],"AAI":[20,64,109,130],"research":[21],"in":[22,129],"languages":[23,132],"other":[24],"than":[25,89,100],"English":[26,59],"scarce":[28],"due":[29],"to":[30,87],"challenges":[32],"collecting":[34],"articulatory":[35,60,135],"data.":[36,136],"In":[37],"recent":[38],"years,":[39],"self-supervised":[40],"learning":[41],"(SSL)":[42],"based":[43],"representations":[44,57],"have":[45],"shown":[46],"great":[47],"for":[49,62,70,126,131],"addressing":[50],"low-resource":[51],"tasks.":[52],"We":[53,91],"utilize":[54],"wav2vec":[55],"2.0":[56],"and":[58,66,103],"data":[61,107],"training":[63],"systems":[65],"investigates":[67],"their":[68],"effectiveness":[69],"a":[71],"different":[72],"language:":[73],"Dutch.":[74],"Results":[75],"show":[76],"that":[77,93],"using":[78],"mms-1b":[79],"features":[80],"can":[81],"reduce":[82],"cross-lingual":[84],"performance":[85],"drop":[86],"less":[88],"30%.":[90],"found":[92],"increasing":[94],"model":[95],"size,":[96],"selecting":[97],"intermediate":[98],"rather":[99],"final":[101],"layers,":[102],"including":[104],"more":[105],"pre-training":[106],"improved":[108],"performance.":[110],"By":[111],"contrast,":[112],"fine-tuning":[113],"on":[114],"an":[115],"ASR":[116],"task":[117],"did":[118],"not.":[119],"Our":[120],"results":[121],"therefore":[122],"highlight":[123],"promising":[124],"prospects":[125],"implementing":[127],"SSL":[128],"with":[133],"limited":[134]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}