{"id":"https://openalex.org/W2124758433","doi":"https://doi.org/10.1109/icassp.2011.5947660","title":"Automatic Language Identification in music videos with low level audio and visual features","display_name":"Automatic Language Identification in music videos with low level audio and visual features","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2124758433","doi":"https://doi.org/10.1109/icassp.2011.5947660","mag":"2124758433"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5103502228","display_name":"Vijay Chandrasekhar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vijay Chandrasekhar","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","Google Inc., 1600 Amphitheatre Parkway, Mountain View , CA , 94043 , USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View , CA , 94043 , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015357395","display_name":"Mehmet Emre Sargin","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Emre Sargin","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","Google Inc., 1600 Amphitheatre Parkway, Mountain View , CA , 94043 , USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View , CA , 94043 , USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060417276","display_name":"David A. Ross","orcid":"https://orcid.org/0000-0001-8073-8053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David A. Ross","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA","Google Inc., 1600 Amphitheatre Parkway, Mountain View , CA , 94043 , USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., 1600 Amphitheatre Parkway, Mountain View , CA , 94043 , USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103502228"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.2249,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.80038592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9908999800682068,"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/T10860","display_name":"Speech and Audio Processing","score":0.9850999712944031,"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":0.7701196670532227},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6327596306800842},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6260986924171448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44691428542137146},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.42968010902404785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3994542360305786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701196670532227},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6327596306800842},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6260986924171448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44691428542137146},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.42968010902404785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3994542360305786},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W99528949","https://openalex.org/W99956014","https://openalex.org/W135838486","https://openalex.org/W187037124","https://openalex.org/W1558802035","https://openalex.org/W1861213619","https://openalex.org/W1966273763","https://openalex.org/W1993482042","https://openalex.org/W2038219201","https://openalex.org/W2043257208","https://openalex.org/W2097829254","https://openalex.org/W2100588357","https://openalex.org/W2107528709","https://openalex.org/W2142730757","https://openalex.org/W2146194791","https://openalex.org/W2161969291","https://openalex.org/W2172287020","https://openalex.org/W2395544453","https://openalex.org/W2533739470","https://openalex.org/W2911328017","https://openalex.org/W6604047900","https://openalex.org/W6604053933","https://openalex.org/W6605595087","https://openalex.org/W6607624625","https://openalex.org/W6633523743","https://openalex.org/W6639295471","https://openalex.org/W6674571087","https://openalex.org/W6676138327"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519","https://openalex.org/W2801048620"],"abstract_inverted_index":{"Automatic":[0],"Language":[1],"Identification":[2],"(LID)":[3],"in":[4,13,22],"music":[5,23,57],"has":[6],"received":[7],"significantly":[8],"less":[9],"attention":[10],"than":[11],"LID":[12,21],"speech.":[14],"Here,":[15],"we":[16],"study":[17],"the":[18],"problem":[19],"of":[20,55],"videos":[24,58],"uploaded":[25],"on":[26,34],"YouTube.":[27],"We":[28],"use":[29],"a":[30,53],"\u201cbag-of-words\u201d":[31],"approach":[32],"based":[33,37],"state-of-the-art":[35],"content":[36],"audio-visual":[38],"features":[39],"and":[40,59],"linear":[41],"SVM":[42],"classifiers":[43],"for":[44,52],"automatic":[45],"LID.":[46],"Our":[47],"system":[48],"obtains":[49],"48%":[50],"accuracy":[51],"corpus":[54],"25000":[56],"25":[60],"different":[61],"languages.":[62]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}