{"id":"https://openalex.org/W4412377007","doi":"https://doi.org/10.1145/3726302.3730136","title":"Navigating Speech Recording Collections with AI-Generated Illustrations","display_name":"Navigating Speech Recording Collections with AI-Generated Illustrations","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412377007","doi":"https://doi.org/10.1145/3726302.3730136"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730136","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730136","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730136","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730136","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118969095","display_name":"Sirina H\u00e5land","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sirina H\u00e5land","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"raw_orcid":"https://orcid.org/0009-0005-1076-0921","affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118969096","display_name":"Trond Karlsen Str\u00f8m","orcid":null},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Trond Karlsen Str\u00f8m","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"raw_orcid":"https://orcid.org/0009-0000-5070-7758","affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025446188","display_name":"Petra Galu\u0161\u010d\u00e1kov\u00e1","orcid":"https://orcid.org/0000-0001-6328-7131"},"institutions":[{"id":"https://openalex.org/I92008406","display_name":"University of Stavanger","ror":"https://ror.org/02qte9q33","country_code":"NO","type":"education","lineage":["https://openalex.org/I92008406"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Petra Galu\u0161\u010d\u00e1kov\u00e1","raw_affiliation_strings":["University of Stavanger, Stavanger, Norway"],"raw_orcid":"https://orcid.org/0000-0001-6328-7131","affiliations":[{"raw_affiliation_string":"University of Stavanger, Stavanger, Norway","institution_ids":["https://openalex.org/I92008406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92008406"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4020","last_page":"4024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991000294685364,"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":0.992900013923645,"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/T11309","display_name":"Music and Audio Processing","score":0.991599977016449,"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/computer-science","display_name":"Computer science","score":0.7252485752105713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5259031653404236},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3434714078903198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252485752105713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5259031653404236},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3434714078903198}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3726302.3730136","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730136","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730136","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.04182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04182","pdf_url":"https://arxiv.org/pdf/2507.04182","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730136","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730136","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730136","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412377007.pdf","grobid_xml":"https://content.openalex.org/works/W4412377007.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W14941018","https://openalex.org/W1980498125","https://openalex.org/W2771976988","https://openalex.org/W2799473636","https://openalex.org/W3093699630","https://openalex.org/W3101648800","https://openalex.org/W4391287689","https://openalex.org/W4391287701","https://openalex.org/W4399428321","https://openalex.org/W4403577870","https://openalex.org/W4414448986","https://openalex.org/W6851487454","https://openalex.org/W6861216459"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Although":[0],"the":[1,96,122,127],"amount":[2],"of":[3,108,129],"available":[4],"spoken":[5,38],"content":[6,39],"is":[7,93],"steadily":[8],"increasing,":[9],"extracting":[10],"information":[11,22],"and":[12,29,36,44,64,87,105],"knowledge":[13],"from":[14],"speech":[15,27,56,103,131],"recordings":[16],"remains":[17],"challenging.":[18],"Beyond":[19],"enhancing":[20],"traditional":[21],"retrieval":[23],"methods":[24],"such":[25],"as":[26],"search":[28],"keyword":[30],"spotting,":[31],"novel":[32,52],"approaches":[33],"for":[34,55],"navigating":[35],"searching":[37],"need":[40],"to":[41,125],"be":[42],"explored":[43],"developed.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"a":[51,73,80,115],"navigational":[53],"method":[54],"archives":[57],"that":[58,76],"leverages":[59],"recent":[60],"advances":[61],"in":[62],"language":[63],"multimodal":[65],"generative":[66],"models.":[67],"We":[68],"demonstrate":[69],"our":[70],"approach":[71],"with":[72],"Web":[74],"application":[75],"organizes":[77],"data":[78],"into":[79],"structured":[81],"format":[82],"using":[83,95,114],"interactive":[84],"mind":[85],"maps":[86],"image":[88],"generation":[89],"tools.":[90],"The":[91],"system":[92],"implemented":[94],"TED-LIUM~3":[97],"dataset,":[98],"which":[99],"comprises":[100],"over":[101],"2,000":[102],"transcripts":[104],"audio":[106],"files":[107],"TED":[109],"Talks.":[110],"Initial":[111],"user":[112],"tests":[113],"System":[116],"Usability":[117],"Scale":[118],"(SUS)":[119],"questionnaire":[120],"indicate":[121],"application's":[123],"potential":[124],"simplify":[126],"exploration":[128],"large":[130],"collections.":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
