{"id":"https://openalex.org/W4379806228","doi":"https://doi.org/10.1145/3591106.3592270","title":"Multimodal Topic Segmentation of Podcast Shows with Pre-trained Neural Encoders","display_name":"Multimodal Topic Segmentation of Podcast Shows with Pre-trained Neural Encoders","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806228","doi":"https://doi.org/10.1145/3591106.3592270"},"language":"en","primary_location":{"id":"doi:10.1145/3591106.3592270","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","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/A5092114884","display_name":"Iacopo Ghinassi","orcid":"https://orcid.org/0000-0002-7409-7736"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Iacopo Ghinassi","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-7409-7736","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403109","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0001-8095-9518"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-8095-9518","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063973385","display_name":"Chris Newell","orcid":"https://orcid.org/0009-0001-7235-9130"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chris Newell","raw_affiliation_strings":["R&amp;D, BBC, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0001-7235-9130","affiliations":[{"raw_affiliation_string":"R&amp;D, BBC, United Kingdom","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047970122","display_name":"Matthew Purver","orcid":"https://orcid.org/0000-0003-2297-1273"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["GB","SI"],"is_corresponding":false,"raw_author_name":"Matthew Purver","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom and Institut Jo\u017eef Stefan, Slovenia"],"raw_orcid":"https://orcid.org/0000-0003-2297-1273","affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom and Institut Jo\u017eef Stefan, Slovenia","institution_ids":["https://openalex.org/I166337079","https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092114884"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":1.1514,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7812442,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"602","last_page":"606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9865999817848206,"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/T13321","display_name":"Radio, Podcasts, and Digital Media","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8226935863494873},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7621346116065979},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.709770917892456},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7083461284637451},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.7019988298416138},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.6443199515342712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5769016742706299},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5202887654304504},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5178828239440918},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3485383987426758}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226935863494873},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7621346116065979},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.709770917892456},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7083461284637451},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.7019988298416138},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.6443199515342712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5769016742706299},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5202887654304504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5178828239440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3485383987426758},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3591106.3592270","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/89320","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/89320","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3331660073","display_name":null,"funder_award_id":"EP/S033564/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3815955973","display_name":null,"funder_award_id":"EP/W001632/1 and EP/S033564/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W140783384","https://openalex.org/W2064675550","https://openalex.org/W2093121049","https://openalex.org/W2099467003","https://openalex.org/W2106918957","https://openalex.org/W2140836433","https://openalex.org/W2167055684","https://openalex.org/W2746152375","https://openalex.org/W2761764495","https://openalex.org/W2890964092","https://openalex.org/W2914694065","https://openalex.org/W2939574508","https://openalex.org/W2962716111","https://openalex.org/W2963351448","https://openalex.org/W3005801733","https://openalex.org/W3086755561","https://openalex.org/W3102373121","https://openalex.org/W3172351783","https://openalex.org/W3201191346","https://openalex.org/W4242213453","https://openalex.org/W4297499129","https://openalex.org/W6893731396"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"We":[0,18,47],"present":[1],"two":[2,57,75],"multimodal":[3,86],"models":[4],"for":[5,88],"topic":[6,89],"segmentation":[7],"of":[8],"podcasts":[9],"built":[10],"on":[11],"pre-trained":[12],"neural":[13],"text":[14],"and":[15,64,83],"audio":[16,51],"embeddings.":[17],"show":[19,49],"that":[20,50],"results":[21],"can":[22,53],"be":[23,54],"improved":[24],"by":[25,31],"combining":[26,32],"different":[27,33],"modalities;":[28],"but":[29],"also":[30,48],"encoders":[34],"from":[35],"the":[36,77],"same":[37],"modality,":[38],"especially":[39],"general-purpose":[40],"sentence":[41,62],"embeddings":[42,52],"with":[43,56,67],"specifically":[44],"fine-tuned":[45],"ones.":[46],"substituted":[55],"simple":[58],"features":[59],"related":[60],"to":[61],"duration":[63],"inter-sentential":[65],"pauses":[66],"comparable":[68],"results.":[69],"Finally,":[70],"we":[71],"publicly":[72,82],"release":[73],"our":[74,80],"datasets,":[76],"first":[78],"in":[79],"knowledge":[81],"freely":[84],"available":[85],"datasets":[87],"segmentation.":[90]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
