{"id":"https://openalex.org/W4416067594","doi":"https://doi.org/10.1007/978-981-95-4395-3_20","title":"Optimal Transport Regularization for\u00a0Speech Text Alignment in\u00a0Spoken Language Models","display_name":"Optimal Transport Regularization for\u00a0Speech Text Alignment in\u00a0Spoken Language Models","publication_year":2025,"publication_date":"2025-11-10","ids":{"openalex":"https://openalex.org/W4416067594","doi":"https://doi.org/10.1007/978-981-95-4395-3_20"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-95-4395-3_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4395-3_20","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5104217897","display_name":"Wenpu Xu","orcid":"https://orcid.org/0009-0005-3014-2901"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Wenze Xu","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd., Chongqing, China","The University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd., Chongqing, China","institution_ids":[]},{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111265915","display_name":"Chun Wang","orcid":"https://orcid.org/0009-0007-2290-910X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun Wang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd., Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd., Chongqing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042100011","display_name":"Jiazhen Yu","orcid":"https://orcid.org/0009-0003-1282-3776"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Jiazhen Yu","raw_affiliation_strings":["Macau University of Science and Technology, Macau SAR, China"],"affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology, Macau SAR, China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320982","display_name":"Sheng Chen","orcid":"https://orcid.org/0009-0002-0397-3935"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Chen","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd., Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd., Chongqing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101115229","display_name":"Liang Gao","orcid":"https://orcid.org/0009-0005-6408-5271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Gao","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd., Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd., Chongqing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025452586","display_name":"Weihong Deng","orcid":"https://orcid.org/0000-0001-5952-6996"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weihong Deng","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd., Chongqing, China"],"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd., Chongqing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104217897"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54420812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"294"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6575000286102295,"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":0.6575000286102295,"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/T10028","display_name":"Topic Modeling","score":0.06729999929666519,"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":0.029999999329447746,"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/regularization","display_name":"Regularization (linguistics)","score":0.7311999797821045},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.5512999892234802},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5227000117301941},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5078999996185303},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47850000858306885},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41440001130104065},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.38350000977516174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614000082015991},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7311999797821045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5227000117301941},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-95-4395-3_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-95-4395-3_20","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","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":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W3034332156","https://openalex.org/W3095410713","https://openalex.org/W3153583341","https://openalex.org/W3196509775","https://openalex.org/W4319862635","https://openalex.org/W4385570154","https://openalex.org/W4385570757","https://openalex.org/W4391021666","https://openalex.org/W4401042284","https://openalex.org/W4402670519","https://openalex.org/W4410771025","https://openalex.org/W4412171133"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-10T00:00:00"}
