{"id":"https://openalex.org/W4414373247","doi":"https://doi.org/10.1007/978-3-032-04947-6_59","title":"Speech Audio Generation from\u00a0Dynamic MRI via\u00a0a\u00a0Knowledge Enhanced Conditional Variational Autoencoder","display_name":"Speech Audio Generation from\u00a0Dynamic MRI via\u00a0a\u00a0Knowledge Enhanced Conditional Variational Autoencoder","publication_year":2025,"publication_date":"2025-09-20","ids":{"openalex":"https://openalex.org/W4414373247","doi":"https://doi.org/10.1007/978-3-032-04947-6_59"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-04947-6_59","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-04947-6_59","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5053699306","display_name":"Yaxuan Li","orcid":"https://orcid.org/0000-0001-9882-6756"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yaxuan Li","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101690252","display_name":"Han Jiang","orcid":"https://orcid.org/0000-0002-7112-4081"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jiang","raw_affiliation_strings":["School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, Xi\u2019an Jiaotong University, Xi\u2019an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101697426","display_name":"Yifei Ma","orcid":"https://orcid.org/0000-0001-6918-781X"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yifei Ma","raw_affiliation_strings":["Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Hong Kong, Pokfulam, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113408848","display_name":"S. N. Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shihua Qin","raw_affiliation_strings":["Medical Center Boulevard, Wake Forest University School of Medicine, Winston-Salem, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Center Boulevard, Wake Forest University School of Medicine, Winston-Salem, NC, USA","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491780","display_name":"Jonghye Woo","orcid":"https://orcid.org/0000-0002-5621-9218"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonghye Woo","raw_affiliation_strings":["Department of Radiology, Harvard Medical School, Boston, 08544, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Harvard Medical School, Boston, 08544, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007259734","display_name":"Fangxu Xing","orcid":"https://orcid.org/0000-0002-0517-0952"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fangxu Xing","raw_affiliation_strings":["Department of Radiology, Harvard Medical School, Boston, 08544, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Harvard Medical School, Boston, 08544, USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007259734"],"corresponding_institution_ids":["https://openalex.org/I136199984"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"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":"619","last_page":"629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6517000198364258},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6236000061035156},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5044000148773193},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.46799999475479126},{"id":"https://openalex.org/keywords/dynamic-contrast-enhanced-mri","display_name":"Dynamic contrast-enhanced MRI","score":0.461899995803833},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4496999979019165},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40299999713897705},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3749000132083893},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.37470000982284546},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.37369999289512634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8784000277519226},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6517000198364258},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6236000061035156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5950999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5205000042915344},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C41727105","wikidata":"https://www.wikidata.org/wiki/Q17009718","display_name":"Dynamic contrast-enhanced MRI","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4496999979019165},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.37470000982284546},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.36970001459121704},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C157787499","wikidata":"https://www.wikidata.org/wiki/Q13479657","display_name":"Real-time MRI","level":3,"score":0.3481999933719635},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.34380000829696655},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3174000084400177},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.27959999442100525},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.27549999952316284},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26460000872612},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-04947-6_59","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-032-04947-6_59","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2028971373","https://openalex.org/W2054139811","https://openalex.org/W2095619674","https://openalex.org/W2165625504","https://openalex.org/W2513720557","https://openalex.org/W2593414223","https://openalex.org/W2898170006","https://openalex.org/W2898906856","https://openalex.org/W2963113682","https://openalex.org/W2964352155","https://openalex.org/W2975624419","https://openalex.org/W3035626590","https://openalex.org/W3130860000","https://openalex.org/W3138516171","https://openalex.org/W3171007011","https://openalex.org/W3183290900","https://openalex.org/W4293708185","https://openalex.org/W4307352693","https://openalex.org/W4386494260","https://openalex.org/W4387211585","https://openalex.org/W4391454452"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}