{"id":"https://openalex.org/W2770372655","doi":"https://doi.org/10.18420/in2017_10","title":"Automatic speech/music discrimination for broadcast signals","display_name":"Automatic speech/music discrimination for broadcast signals","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2770372655","doi":"https://doi.org/10.18420/in2017_10","mag":"2770372655"},"language":"en","primary_location":{"id":"pmh:oai:fraunhofer.de:N-481500","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-481500.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://publica.fraunhofer.de/documents/N-481500.html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050670407","display_name":"Anna Kruspe","orcid":"https://orcid.org/0000-0002-2041-9453"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kruspe, Anna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051573555","display_name":"Dominik Zapf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zapf, Dominik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067411318","display_name":"Hanna Lukashevich","orcid":"https://orcid.org/0000-0002-9041-9475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lukashevich, Hanna","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050670407"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66846064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.995199978351593,"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/speech-recognition","display_name":"Speech recognition","score":0.6548009514808655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4766986072063446},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.34367960691452026},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.33622145652770996},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22809556126594543}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6548009514808655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4766986072063446},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.34367960691452026},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.33622145652770996},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22809556126594543},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:fraunhofer.de:N-481500","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-481500.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/399531","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/399531","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"},{"id":"doi:10.18420/in2017_10","is_oa":true,"landing_page_url":"https://doi.org/10.18420/in2017_10","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2770372655","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/gi/gi2017.html#KruspeZL17","pdf_url":null,"source":{"id":"https://openalex.org/S4306511462","display_name":"GI-Jahrestagung","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"GI-Jahrestagung","raw_type":null}],"best_oa_location":{"id":"pmh:oai:fraunhofer.de:N-481500","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-481500.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6100000143051147,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W166844666","https://openalex.org/W1600222083","https://openalex.org/W1980993072","https://openalex.org/W1995341919","https://openalex.org/W2049633694","https://openalex.org/W2103253424","https://openalex.org/W2106055371","https://openalex.org/W2123577100","https://openalex.org/W2124864596","https://openalex.org/W2154100244","https://openalex.org/W2407888529","https://openalex.org/W2593116425","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2013484580","https://openalex.org/W2313975570","https://openalex.org/W2326706203","https://openalex.org/W2883903999","https://openalex.org/W2004158276","https://openalex.org/W2834591099","https://openalex.org/W2876662273","https://openalex.org/W3150877489","https://openalex.org/W2121103546","https://openalex.org/W2941910597","https://openalex.org/W155616691","https://openalex.org/W2050101927","https://openalex.org/W2052675777","https://openalex.org/W2005675599","https://openalex.org/W2854217123","https://openalex.org/W2035330281","https://openalex.org/W3144292193","https://openalex.org/W1525119209","https://openalex.org/W2154843555","https://openalex.org/W1541790149"],"abstract_inverted_index":{"Automatic":[0],"speech/music":[1,122],"discrimination":[2,76],"describes":[3],"the":[4,50,72,113,116,119,147],"task":[5],"of":[6,23,52,118,121,133,149],"automatically":[7],"detecting":[8],"speech":[9],"and":[10,28,94,115,139],"music":[11,53],"audio":[12,103,134],"within":[13],"a":[14,20,131],"recording.":[15],"This":[16],"is":[17,77],"useful":[18],"for":[19,37,61,66,146],"great":[21],"number":[22],"tasks":[24],"in":[25,46],"both":[26],"research":[27,151],"industry.":[29],"In":[30,105],"particular,":[31],"this":[32,106,153],"approach":[33],"can":[34,57,95],"be":[35,59,97],"used":[36,60,98],"broadcast":[38],"signals":[39],"(e.g.":[40,65],"from":[41],"TV":[42],"or":[43],"radio":[44],"stations)":[45],"order":[47],"to":[48,99],"determine":[49],"amount":[51],"played.":[54],"The":[55],"results":[56],"then":[58,96],"various":[62],"reporting":[63],"purposes":[64],"royalty":[67],"collection":[68],"societies":[69],"such":[70],"as":[71],"German":[73],"GEMA).":[74],"Speech/music":[75],"commonly":[78],"performed":[79],"by":[80],"using":[81],"machine":[82],"learning":[83],"technologies,":[84],"where":[85],"models":[86],"are":[87],"first":[88],"trained":[89],"on":[90,130],"manually":[91],"annotated":[92],"data,":[93],"classify":[100],"previously":[101],"unseen":[102],"data.":[104],"paper,":[107],"we":[108,125,143],"give":[109,144],"an":[110],"overview":[111],"over":[112],"applications":[114],"state":[117],"art":[120],"discrimination.":[123],"Afterwards,":[124],"present":[126],"our":[127],"approaches":[128],"based":[129],"set":[132],"features,":[135],"Gaussian":[136],"Mixture":[137],"Models":[138],"Deep":[140],"Learning.":[141],"Finally,":[142],"suggestions":[145],"direction":[148],"new":[150],"into":[152],"topic.":[154]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}