{"id":"https://openalex.org/W4400942795","doi":"https://doi.org/10.7148/2024-0550","title":"Vggish for music/speech classification in radio broadcasting","display_name":"Vggish for music/speech classification in radio broadcasting","publication_year":2024,"publication_date":"2024-06-07","ids":{"openalex":"https://openalex.org/W4400942795","doi":"https://doi.org/10.7148/2024-0550"},"language":"en","primary_location":{"id":"doi:10.7148/2024-0550","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2024-0550","pdf_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0550_dis_ecms2024_0088.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2024 Proceedings edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0550_dis_ecms2024_0088.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019857437","display_name":"Salvatore Serrano","orcid":"https://orcid.org/0000-0003-0507-5186"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Salvatore Serrano","raw_affiliation_strings":["Department of Engineering , University of Messina ,"],"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina ,","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033292026","display_name":"Marco Scarpa","orcid":"https://orcid.org/0000-0002-9560-7504"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Lucio Scarpa","raw_affiliation_strings":["Department of Engineering , University of Messina ,"],"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina ,","institution_ids":["https://openalex.org/I112862951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021108778","display_name":"Omar Serghini","orcid":"https://orcid.org/0009-0000-4404-9074"},"institutions":[{"id":"https://openalex.org/I112862951","display_name":"University of Messina","ror":"https://ror.org/05ctdxz19","country_code":"IT","type":"education","lineage":["https://openalex.org/I112862951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Omar Serghini","raw_affiliation_strings":["Department of Engineering , University of Messina ,"],"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Messina ,","institution_ids":["https://openalex.org/I112862951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019857437"],"corresponding_institution_ids":["https://openalex.org/I112862951"],"apc_list":null,"apc_paid":null,"fwci":0.3624,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53503117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"550","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9776999950408936,"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/T10860","display_name":"Speech and Audio Processing","score":0.9776999950408936,"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":0.9442999958992004,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/broadcasting","display_name":"Broadcasting (networking)","score":0.7331510186195374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6993366479873657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.55808424949646},{"id":"https://openalex.org/keywords/radio-broadcasting","display_name":"Radio broadcasting","score":0.5118314623832703},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.29067814350128174},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.27026742696762085}],"concepts":[{"id":"https://openalex.org/C110157686","wikidata":"https://www.wikidata.org/wiki/Q922122","display_name":"Broadcasting (networking)","level":2,"score":0.7331510186195374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993366479873657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.55808424949646},{"id":"https://openalex.org/C58911810","wikidata":"https://www.wikidata.org/wiki/Q273623","display_name":"Radio broadcasting","level":2,"score":0.5118314623832703},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.29067814350128174},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.27026742696762085}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.7148/2024-0550","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2024-0550","pdf_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0550_dis_ecms2024_0088.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2024 Proceedings edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.7148/2024-0550","is_oa":true,"landing_page_url":"https://doi.org/10.7148/2024-0550","pdf_url":"http://www.scs-europe.net/dlib/2024/ecms2024acceptedpapers/0550_dis_ecms2024_0088.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ECMS 2024 Proceedings edited by Daniel Grzonka, Natalia Rylko, Grazyna Suchacka, Vladimir Mityushev","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400942795.pdf","grobid_xml":"https://content.openalex.org/works/W4400942795.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4256131726","https://openalex.org/W4379377929","https://openalex.org/W2883419526","https://openalex.org/W610673289","https://openalex.org/W1984632043","https://openalex.org/W2903979341","https://openalex.org/W4206336776","https://openalex.org/W2256522362","https://openalex.org/W2613913289","https://openalex.org/W3190457193"],"abstract_inverted_index":{"In":[0],"the":[1,18,51,88,131,147],"realm":[2],"of":[3,63,82,90,133,149],"audio":[4,40,64,105,154],"signal":[5,155],"processing,":[6],"distinguishing":[7,123],"between":[8,124,139],"music":[9,44,83,125,140],"and":[10,21,54,84,110,126,141],"speech":[11],"poses":[12],"a":[13,60],"significant":[14],"challenge":[15,32],"due":[16],"to":[17,38,58,71,77,146],"nuanced":[19],"similarities":[20],"complexities":[22],"inherent":[23],"in":[24,93,102,122,137,153],"both":[25],"domains.":[26],"This":[27,143],"study":[28],"delves":[29],"into":[30],"this":[31,94],"by":[33],"employing":[34],"deep":[35,134,150],"learning":[36,135,151],"techniques":[37],"classify":[39],"segments":[41],"as":[42,56,69],"either":[43],"or":[45],"speech.":[46,85,127,142],"Our":[47],"approach":[48],"involves":[49],"utilizing":[50],"VGGish":[52],"architecture":[53],"Mel-spectrograms":[55],"input":[57],"provide":[59],"rich":[61],"representations":[62,67],"signals.":[65],"These":[66,128],"serve":[68],"inputs":[70],"our":[72,91],"classification":[73,95],"models,":[74],"enabling":[75],"us":[76],"discern":[78],"intricate":[79],"patterns":[80],"characteristic":[81],"We":[86],"explore":[87],"efficacy":[89],"models":[92,136],"task,":[96],"particularly":[97],"focusing":[98],"on":[99],"their":[100],"performance":[101],"various":[103],"windowed":[104],"segments.":[106],"Through":[107],"rigorous":[108],"experimentation":[109],"evaluation,":[111],"we":[112],"observe":[113],"notable":[114],"results.":[115],"Models":[116],"exhibit":[117],"remarkable":[118],"accuracy,":[119],"exceeding":[120],"$96\\%$":[121],"findings":[129],"underscore":[130],"effectiveness":[132],"discerning":[138],"work":[144],"contributes":[145],"understanding":[148],"applications":[152],"processing.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-12T06:13:28.667946","created_date":"2025-10-10T00:00:00"}
