{"id":"https://openalex.org/W7168900303","doi":"https://doi.org/10.1007/978-981-92-3417-2_6","title":"Sound-Mind: Enhancing Paralinguistic Understanding in MLLMs via Iterative Latent Refinement","display_name":"Sound-Mind: Enhancing Paralinguistic Understanding in MLLMs via Iterative Latent Refinement","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7168900303","doi":"https://doi.org/10.1007/978-981-92-3417-2_6"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-3417-2_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3417-2_6","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/A5028590139","display_name":"Zongzheng Han","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongzheng Han","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133738934","display_name":"X Y Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuwen Yang","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141039078","display_name":"Wei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338337","display_name":"Zi Wang","orcid":"https://orcid.org/0000-0002-7361-1406"},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehua Wang","raw_affiliation_strings":["School of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, 300457, China","School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, 300457, China","institution_ids":["https://openalex.org/I132369690"]},{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141033711","display_name":"Jueting Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jueting Liu","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141039754","display_name":"Tingting Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Xu","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036800252","display_name":"Ziyang Xing","orcid":"https://orcid.org/0000-0003-1442-3680"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyang Xing","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009228524","display_name":"Z Y Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongjian Zhang","raw_affiliation_strings":["School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology / School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5141039078"],"corresponding_institution_ids":[],"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":"61","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.9542999863624573},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.5347999930381775},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5049999952316284},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.46970000863075256},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4383000135421753},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.41839998960494995},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.38499999046325684},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.383899986743927},{"id":"https://openalex.org/keywords/surprise","display_name":"Surprise","score":0.3822999894618988}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.9542999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568000197410583},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5077000260353088},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4560000002384186},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C2780343955","wikidata":"https://www.wikidata.org/wiki/Q333173","display_name":"Surprise","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3675000071525574},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.36649999022483826},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3052999973297119},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.25949999690055847},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-3417-2_6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-3417-2_6","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W2963686995","https://openalex.org/W3209059054","https://openalex.org/W4281492411","https://openalex.org/W4361994820","https://openalex.org/W4381786045","https://openalex.org/W4410061981","https://openalex.org/W4416035790","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-18T05:51:51.687321","created_date":"2026-07-17T00:00:00"}
