{"id":"https://openalex.org/W7148497032","doi":"https://doi.org/10.1109/asru65441.2025.11434615","title":"Improving Multimodal Speech-To-Slide Alignment for Academic Lectures with Vision LLMs","display_name":"Improving Multimodal Speech-To-Slide Alignment for Academic Lectures with Vision LLMs","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148497032","doi":"https://doi.org/10.1109/asru65441.2025.11434615"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5062249053","display_name":"Thomas Ranzenberger","orcid":null},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Thomas Ranzenberger","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016617263","display_name":"Dominik Wagner","orcid":"https://orcid.org/0000-0002-3631-4138"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092662951","display_name":"Steffen Freisinger","orcid":null},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Freisinger","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg,N&#x00FC;rnberg,Germany","institution_ids":["https://openalex.org/I2799978770"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5062249053"],"corresponding_institution_ids":["https://openalex.org/I2799978770"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87572216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.4945000112056732,"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/T12031","display_name":"Speech and dialogue systems","score":0.4945000112056732,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.09529999643564224,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.051100000739097595,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/key","display_name":"Key (lock)","score":0.26190000772476196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38929998874664307},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31450000405311584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C55587333","wikidata":"https://www.wikidata.org/wiki/Q1133029","display_name":"Engineering ethics","level":1,"score":0.28139999508857727},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.26989999413490295},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434615","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1575345398","https://openalex.org/W2051602168","https://openalex.org/W2101121293","https://openalex.org/W2164863177","https://openalex.org/W2167933140","https://openalex.org/W2395433193","https://openalex.org/W2964982818","https://openalex.org/W2970641574","https://openalex.org/W3120043490","https://openalex.org/W4280519175","https://openalex.org/W4285255856","https://openalex.org/W4307030411","https://openalex.org/W4385245566","https://openalex.org/W4387321091","https://openalex.org/W4390872447","https://openalex.org/W4402112257","https://openalex.org/W4404782721","https://openalex.org/W4406461448"],"related_works":[],"abstract_inverted_index":{"We":[0],"enhance":[1],"the":[2,71,80],"MaViLS":[3,82],"multimodal":[4,37],"algorithm":[5],"to":[6,86,99],"improve":[7],"speech-to-slide":[8],"alignment":[9,78],"for":[10,20,40,75],"lecture":[11,28,52],"podcasts.":[12],"Our":[13,68],"approach":[14],"integrates":[15],"vision":[16],"large":[17],"language":[18],"models":[19],"optical":[21],"character":[22],"recognition":[23],"and":[24,42,54,88],"automatic":[25],"generation":[26],"of":[27],"transcripts":[29,53],"from":[30,84,97],"slide":[31,56],"content,":[32],"coupled":[33],"with":[34,49],"a":[35,90],"multilingual":[36],"embedding":[38],"model":[39],"text":[41,48],"image":[43],"alignment.":[44],"By":[45],"combining":[46],"slide-extracted":[47],"automatically":[50],"generated":[51],"captioned":[55],"images,":[57],"we":[58],"generate":[59],"enhanced":[60],"audio":[61,76],"features":[62],"that":[63],"better":[64],"capture":[65],"speech-slide":[66],"mapping.":[67],"method":[69],"improves":[70],"average":[72],"F1":[73],"score":[74],"feature":[77],"on":[79,89],"English":[81],"dataset":[83,96],"0.51":[85],"0.71":[87],"newly":[91],"created":[92],"German":[93],"podcast":[94],"lectures":[95],"0.65":[98],"0.84.":[100]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
