{"id":"https://openalex.org/W3011062822","doi":"https://doi.org/10.1109/icassp40776.2020.9054688","title":"Tensorflow Audio Models in Essentia","display_name":"Tensorflow Audio Models in Essentia","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3011062822","doi":"https://doi.org/10.1109/icassp40776.2020.9054688","mag":"3011062822"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.07393","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085164793","display_name":"Pablo Alonso-Jim\u00e9nez","orcid":"https://orcid.org/0000-0002-4121-5089"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Pablo Alonso-Jimenez","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra","Universitat Pompeu Fabra. Music Technology Group"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra. Music Technology Group","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004451369","display_name":"Dmitry Bogdanov","orcid":"https://orcid.org/0000-0002-9469-0633"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dmitry Bogdanov","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra","Universitat Pompeu Fabra. Music Technology Group"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra. Music Technology Group","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137809","display_name":"Jordi Pons","orcid":"https://orcid.org/0000-0001-9603-0869"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Pons","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra","Universitat Pompeu Fabra. Music Technology Group"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra. Music Technology Group","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra","Universitat Pompeu Fabra. Music Technology Group"],"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra. Music Technology Group","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5085164793"],"corresponding_institution_ids":["https://openalex.org/I170486558"],"apc_list":null,"apc_paid":null,"fwci":0.14777568,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39515758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9962000250816345,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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/computer-science","display_name":"Computer science","score":0.8209154605865479},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8083924055099487},{"id":"https://openalex.org/keywords/extensibility","display_name":"Extensibility","score":0.5733152031898499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5596038103103638},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5455436706542969},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5235083699226379},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.45174217224121094},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4185720384120941},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3917592465877533},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3495032787322998},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.342825710773468},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.14388373494148254},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11509168148040771}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8209154605865479},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8083924055099487},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.5733152031898499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5596038103103638},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5455436706542969},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5235083699226379},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.45174217224121094},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4185720384120941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3917592465877533},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3495032787322998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.342825710773468},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.14388373494148254},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11509168148040771},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/46455","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/46455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/acceptedVersion"},{"id":"pmh:oai:arXiv.org:2003.07393","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.07393","pdf_url":"https://arxiv.org/pdf/2003.07393","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3011062822","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.07393v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.07393","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.07393","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.07393","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.07393","pdf_url":"https://arxiv.org/pdf/2003.07393","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3011062822.pdf","grobid_xml":"https://content.openalex.org/works/W3011062822.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W2385545","https://openalex.org/W14803479","https://openalex.org/W54887220","https://openalex.org/W1499923356","https://openalex.org/W1556219185","https://openalex.org/W1686810756","https://openalex.org/W1781845406","https://openalex.org/W2009365279","https://openalex.org/W2085662862","https://openalex.org/W2109076057","https://openalex.org/W2127870748","https://openalex.org/W2137637927","https://openalex.org/W2191779130","https://openalex.org/W2402144811","https://openalex.org/W2405656250","https://openalex.org/W2518508706","https://openalex.org/W2526050071","https://openalex.org/W2529478963","https://openalex.org/W2586665457","https://openalex.org/W2794150026","https://openalex.org/W2808524943","https://openalex.org/W2899771611","https://openalex.org/W2950060770","https://openalex.org/W2950693330","https://openalex.org/W2962813390","https://openalex.org/W2962845248","https://openalex.org/W2963369619","https://openalex.org/W2963550089","https://openalex.org/W3000400453","https://openalex.org/W6600599976","https://openalex.org/W6602203489","https://openalex.org/W6621935268","https://openalex.org/W6629770511","https://openalex.org/W6637373629","https://openalex.org/W6638109833","https://openalex.org/W6678969435","https://openalex.org/W6713134421","https://openalex.org/W6715395060","https://openalex.org/W6726556977","https://openalex.org/W6728400142","https://openalex.org/W6736327223","https://openalex.org/W6745878906","https://openalex.org/W6756040250","https://openalex.org/W6763945542","https://openalex.org/W6768465061"],"related_works":["https://openalex.org/W3039199168","https://openalex.org/W2908947345","https://openalex.org/W2808040094","https://openalex.org/W2949135528","https://openalex.org/W3197475168","https://openalex.org/W3137061102","https://openalex.org/W2989591473","https://openalex.org/W2996691129","https://openalex.org/W3195521635","https://openalex.org/W2972437240","https://openalex.org/W2977578010","https://openalex.org/W3023289764","https://openalex.org/W2896897713","https://openalex.org/W3034549508","https://openalex.org/W3086860067","https://openalex.org/W3159559013","https://openalex.org/W1548100229","https://openalex.org/W3201362247","https://openalex.org/W3190460602","https://openalex.org/W3095113400"],"abstract_inverted_index":{"Essentia":[0],"is":[1],"a":[2,17,58,86],"reference":[3],"open-source":[4],"C++/Python":[5],"library":[6],"for":[7],"audio":[8],"and":[9,33,43,65],"music":[10,63],"analysis.":[11],"In":[12,78],"this":[13,51],"work,":[14],"we":[15,56,80],"present":[16],"set":[18],"of":[19,39,50,60,74,103],"algorithms":[20],"that":[21],"employ":[22],"TensorFlow":[23],"in":[24,85],"Essentia,":[25],"allow":[26],"predictions":[27],"with":[28,54],"pre-trained":[29,61],"deep":[30],"learning":[31],"models,":[32],"are":[34],"designed":[35],"to":[36,100],"offer":[37],"flexibility":[38],"use,":[40],"easy":[41],"extensibility,":[42],"real-time":[44],"inference.":[45],"To":[46],"show":[47],"the":[48,75,82,101],"potential":[49],"new":[52],"interface":[53],"TensorFlow,":[55],"provide":[57],"number":[59],"state-of-the-art":[62],"tagging":[64],"classification":[66],"CNN":[67],"models.":[68,77,105],"We":[69],"run":[70],"an":[71],"extensive":[72],"evaluation":[73,88],"developed":[76],"particular,":[79],"assess":[81],"generalization":[83],"capabilities":[84],"cross-collection":[87],"utilizing":[89],"both":[90],"external":[91],"tag":[92],"datasets":[93],"as":[94,96],"well":[95],"manual":[97],"annotations":[98],"tailored":[99],"taxonomies":[102],"our":[104]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}