{"id":"https://openalex.org/W4415432738","doi":"https://doi.org/10.21437/interspeech.2025-2792","title":"Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation","display_name":"Towards Multi-Level Transcript Segmentation: LoRA Fine-Tuning for Table-of-Contents Generation","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432738","doi":"https://doi.org/10.21437/interspeech.2025-2792"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2792","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.02128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092662951","display_name":"Steffen Freisinger","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Steffen Freisinger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062589730","display_name":"Philipp Seeberger","orcid":"https://orcid.org/0009-0003-3161-5120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philipp Seeberger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062249053","display_name":"Thomas Ranzenberger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Ranzenberger","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092662951"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31102066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9646999835968018,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9545000195503235,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6809999942779541},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5347999930381775},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5230000019073486},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.44279998540878296},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3601999878883362},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.33970001339912415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70169997215271},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6809999942779541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.558899998664856},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46560001373291016},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.44279998540878296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38100001215934753},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.32659998536109924},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-2792","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.02128","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02128","pdf_url":"https://arxiv.org/pdf/2601.02128","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:kobv.de-opus4-th-nuernberg:4354","is_oa":false,"landing_page_url":"https://opus4.kobv.de/opus4-ohm/frontdoor/index/index/docId/4354","pdf_url":null,"source":{"id":"https://openalex.org/S4306401730","display_name":"OHMdok (Technische Hochschule N\u00fcrnberg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210100612","host_organization_name":"Georg Simon Ohm University of Applied Sciences Nuremberg","host_organization_lineage":["https://openalex.org/I4210100612"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.02128","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.02128","pdf_url":"https://arxiv.org/pdf/2601.02128","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415432738.pdf","grobid_xml":"https://content.openalex.org/works/W4415432738.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Segmenting":[0],"speech":[1,60],"transcripts":[2,71],"into":[3,93],"thematic":[4],"sections":[5],"benefits":[6],"both":[7,37],"downstream":[8],"processing":[9],"and":[10,39,46,68],"users":[11],"who":[12],"depend":[13],"on":[14,49,64],"written":[15],"text":[16],"for":[17,89],"accessibility.":[18],"We":[19,42],"introduce":[20],"a":[21,85],"novel":[22],"approach":[23],"to":[24],"hierarchical":[25,96],"topic":[26,38,79],"segmentation":[27,80],"in":[28],"transcripts,":[29],"generating":[30],"multi-level":[31,90],"tables":[32],"of":[33,58],"contents":[34],"that":[35],"capture":[36],"subtopic":[40],"boundaries.":[41],"compare":[43],"zero-shot":[44],"prompting":[45],"LoRA":[47],"fine-tuning":[48],"large":[50],"language":[51],"models,":[52],"while":[53],"also":[54],"exploring":[55],"the":[56],"integration":[57],"high-level":[59],"pause":[61],"features.":[62],"Evaluations":[63],"English":[65],"meeting":[66],"recordings":[67],"multilingual":[69],"lecture":[70],"(Portuguese,":[72],"German)":[73],"show":[74],"significant":[75],"improvements":[76],"over":[77],"established":[78],"baselines.":[81],"Additionally,":[82],"we":[83],"adapt":[84],"common":[86],"evaluation":[87],"measure":[88],"segmentation,":[91],"taking":[92],"account":[94],"all":[95],"levels":[97],"within":[98],"one":[99],"metric.":[100]},"counts_by_year":[],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-24T00:00:00"}