{"id":"https://openalex.org/W4229057963","doi":"https://doi.org/10.1145/3477314.3507106","title":"Leveraging multimodal content for podcast summarization","display_name":"Leveraging multimodal content for podcast summarization","publication_year":2022,"publication_date":"2022-04-25","ids":{"openalex":"https://openalex.org/W4229057963","doi":"https://doi.org/10.1145/3477314.3507106"},"language":"en","primary_location":{"id":"doi:10.1145/3477314.3507106","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507106","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","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/A5082357372","display_name":"Lorenzo Vaiani","orcid":"https://orcid.org/0000-0002-3605-1577"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Vaiani","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001746215","display_name":"Luca Cagliero","orcid":"https://orcid.org/0000-0002-7185-5247"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Cagliero","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074057809","display_name":"Paolo Garza","orcid":"https://orcid.org/0000-0002-1263-7522"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Politecnico di Torino","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Garza","raw_affiliation_strings":["Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":1.2102,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81051306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9908000230789185,"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":0.9908000230789185,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9721999764442444,"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":0.9415000081062317,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9605283737182617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8659053444862366},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6979745030403137},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5286957025527954},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43994495272636414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4110527038574219},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3952876031398773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.378088116645813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37046027183532715},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32730162143707275},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08956396579742432}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9605283737182617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8659053444862366},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6979745030403137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5286957025527954},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43994495272636414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4110527038574219},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3952876031398773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.378088116645813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37046027183532715},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32730162143707275},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08956396579742432},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3477314.3507106","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3477314.3507106","pdf_url":null,"source":{"id":"https://openalex.org/S4363608665","display_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W30990998","https://openalex.org/W1981974552","https://openalex.org/W2026012689","https://openalex.org/W2060724430","https://openalex.org/W2097321121","https://openalex.org/W2105395363","https://openalex.org/W2167277498","https://openalex.org/W2759570332","https://openalex.org/W2760577196","https://openalex.org/W2939558422","https://openalex.org/W2943038672","https://openalex.org/W2962785754","https://openalex.org/W2963341956","https://openalex.org/W2963389687","https://openalex.org/W2970419734","https://openalex.org/W2970641574","https://openalex.org/W3035050380","https://openalex.org/W3044575351","https://openalex.org/W3085629518","https://openalex.org/W3113822960","https://openalex.org/W3156205755","https://openalex.org/W3176112445","https://openalex.org/W3199294715"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W4289143854"],"abstract_inverted_index":{"Podcasts":[0],"are":[1],"becoming":[2],"an":[3,68,90],"increasingly":[4],"popular":[5],"way":[6],"to":[7,84],"share":[8],"streaming":[9],"audio":[10,37],"content.":[11],"Podcast":[12],"summarization":[13,43,73],"aims":[14],"at":[15],"improving":[16],"the":[17,50,54,59],"accessibility":[18],"of":[19,29,41,49],"podcast":[20,55,64],"content":[21],"by":[22,39],"automatically":[23],"generating":[24],"a":[25],"concise":[26],"summary":[27],"consisting":[28],"text/audio":[30],"extracts.":[31],"Existing":[32],"approaches":[33],"either":[34],"extract":[35],"short":[36],"snippets":[38],"means":[40],"speech":[42,51],"techniques":[44],"or":[45],"produce":[46],"abstractive":[47],"summaries":[48],"transcription":[52],"disregarding":[53],"audio.":[56],"To":[57],"leverage":[58],"multimodal":[60,87],"information":[61],"hidden":[62],"in":[63],"episodes":[65],"we":[66],"propose":[67],"end-to-end":[69],"architecture":[70],"for":[71],"extractive":[72],"that":[74],"encodes":[75],"both":[76],"acoustic":[77],"and":[78],"textual":[79],"contents.":[80],"It":[81],"learns":[82],"how":[83],"attend":[85],"relevant":[86],"features":[88],"using":[89],"ad":[91],"hoc,":[92],"deep":[93],"feature":[94],"fusion":[95],"network.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}