{"id":"https://openalex.org/W4402111630","doi":"https://doi.org/10.21437/interspeech.2024-1864","title":"Optical Flow Guided Tongue Trajectory Generation for Diffusion-based Acoustic to Articulatory Inversion","display_name":"Optical Flow Guided Tongue Trajectory Generation for Diffusion-based Acoustic to Articulatory Inversion","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111630","doi":"https://doi.org/10.21437/interspeech.2024-1864"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1864","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1864","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100933548","display_name":"Yu-Dong Yang","orcid":"https://orcid.org/0009-0005-3048-176X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yudong Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036142381","display_name":"Rongfeng Su","orcid":"https://orcid.org/0000-0002-7228-5768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rongfeng Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038203155","display_name":"Rukiye Ruzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rukiye Ruzi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017148935","display_name":"Manwa L. Ng","orcid":"https://orcid.org/0000-0002-3174-8412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manwa Ng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100943358","display_name":"Shaofeng Zhao","orcid":"https://orcid.org/0009-0008-0711-6029"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaofeng Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109794811","display_name":"Nan Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595942","display_name":"Lan Wang","orcid":"https://orcid.org/0009-0007-4282-6707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan Wang","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9915000200271606,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9915000200271606,"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":0.6507014036178589},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.6427066922187805},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.5908612608909607},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5849356055259705},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5048537850379944},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.44535452127456665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40391743183135986},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2972400188446045},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.1612793505191803},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15399938821792603}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507014036178589},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.6427066922187805},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.5908612608909607},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5849356055259705},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5048537850379944},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.44535452127456665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40391743183135986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2972400188446045},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.1612793505191803},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15399938821792603},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1864","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-1864","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3136794468","https://openalex.org/W2367950022","https://openalex.org/W2365707941","https://openalex.org/W2366141844","https://openalex.org/W2383946220","https://openalex.org/W2358428239","https://openalex.org/W3011636953","https://openalex.org/W2351206852","https://openalex.org/W3212410916","https://openalex.org/W3006862861"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
