{"id":"https://openalex.org/W3206162967","doi":"https://doi.org/10.1109/icassp43922.2022.9747742","title":"Study of Positional Encoding Approaches for Audio Spectrogram Transformers","display_name":"Study of Positional Encoding Approaches for Audio Spectrogram Transformers","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206162967","doi":"https://doi.org/10.1109/icassp43922.2022.9747742","mag":"3206162967"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747742","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.06999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077063899","display_name":"Leonardo Pepino","orcid":"https://orcid.org/0000-0001-5037-3700"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Leonardo Pepino","raw_affiliation_strings":["CONICET-UBA,Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC),Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CONICET-UBA,Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC),Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004397011","display_name":"Pablo Riera","orcid":null},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Pablo Riera","raw_affiliation_strings":["CONICET-UBA,Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC),Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CONICET-UBA,Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC),Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I151201029","display_name":"Consejo Nacional de Investigaciones Cient\u00edficas y T\u00e9cnicas","ror":"https://ror.org/03cqe8w59","country_code":"AR","type":"government","lineage":["https://openalex.org/I151201029","https://openalex.org/I4210123736","https://openalex.org/I4387155568"]},{"id":"https://openalex.org/I4210144290","display_name":"Institute of Astronomy and Space Physics","ror":"https://ror.org/03rq94151","country_code":"AR","type":"facility","lineage":["https://openalex.org/I151201029","https://openalex.org/I24354313","https://openalex.org/I4210123736","https://openalex.org/I4210144290","https://openalex.org/I4387155568"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["CONICET-UBA,Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC),Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CONICET-UBA,Instituto de Investigaci&#x00F3;n en Ciencias de la Computaci&#x00F3;n (ICC),Argentina","institution_ids":["https://openalex.org/I151201029","https://openalex.org/I4210144290"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3713","last_page":"3717"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9987000226974487,"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/spectrogram","display_name":"Spectrogram","score":0.8929538726806641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486958503723145},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7418326139450073},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5959815382957458},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5395762920379639},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.531850278377533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5222783088684082},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4125153720378876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34627336263656616},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3314446806907654},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2594703435897827},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11433497071266174}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8929538726806641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486958503723145},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7418326139450073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5959815382957458},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5395762920379639},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.531850278377533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5222783088684082},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4125153720378876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34627336263656616},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3314446806907654},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2594703435897827},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11433497071266174},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747742","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.06999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.06999","pdf_url":"https://arxiv.org/pdf/2110.06999","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.06999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.06999","pdf_url":"https://arxiv.org/pdf/2110.06999","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"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":59,"referenced_works":["https://openalex.org/W36434594","https://openalex.org/W2031489346","https://openalex.org/W2052666245","https://openalex.org/W2162888803","https://openalex.org/W2593116425","https://openalex.org/W2768188490","https://openalex.org/W2797583228","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2962793908","https://openalex.org/W2963173418","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963925437","https://openalex.org/W2964328535","https://openalex.org/W3015974384","https://openalex.org/W3034886385","https://openalex.org/W3036601975","https://openalex.org/W3040498734","https://openalex.org/W3093494400","https://openalex.org/W3094502228","https://openalex.org/W3097777922","https://openalex.org/W3098903812","https://openalex.org/W3099782249","https://openalex.org/W3104240813","https://openalex.org/W3119786062","https://openalex.org/W3129576130","https://openalex.org/W3130071011","https://openalex.org/W3137278571","https://openalex.org/W3139049060","https://openalex.org/W3139240716","https://openalex.org/W3155806510","https://openalex.org/W3158129762","https://openalex.org/W3164279099","https://openalex.org/W3170016573","https://openalex.org/W3170227631","https://openalex.org/W3196318247","https://openalex.org/W3196974791","https://openalex.org/W3205743929","https://openalex.org/W4287019748","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6745930336","https://openalex.org/W6747753452","https://openalex.org/W6749107692","https://openalex.org/W6750665317","https://openalex.org/W6755207826","https://openalex.org/W6755406732","https://openalex.org/W6778883912","https://openalex.org/W6779503413","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791832345","https://openalex.org/W6792695861","https://openalex.org/W6793987055","https://openalex.org/W6794463088","https://openalex.org/W6800569930"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2066741154","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2530685530","https://openalex.org/W2385135707","https://openalex.org/W4375868962","https://openalex.org/W1546240199","https://openalex.org/W2588117228","https://openalex.org/W614822286"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"revolutionized":[2],"the":[3,10,17,31,58,60,69,96],"world":[4],"of":[5,12,30,57,71],"deep":[6],"learning,":[7],"specially":[8],"in":[9,34,38],"field":[11],"natural":[13],"language":[14],"processing.":[15],"Recently,":[16],"Audio":[18],"Spectrogram":[19],"Transformer":[20],"(AST)":[21],"was":[22],"proposed":[23],"for":[24,40],"audio":[25],"classification,":[26],"leading":[27],"to":[28,42,67,95],"state":[29],"art":[32],"results":[33],"several":[35,65],"datasets.":[36],"However,":[37],"order":[39],"ASTs":[41,72],"outperform":[43],"CNNs,":[44],"pretraining":[45],"with":[46],"ImageNet":[47,77],"is":[48],"needed.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"study":[54],"one":[55],"component":[56],"AST,":[59],"positional":[61,85],"encoding,":[62],"and":[63,92],"propose":[64],"variants":[66],"improve":[68],"performance":[70,89],"trained":[73],"from":[74],"scratch,":[75],"without":[76],"pretraining.":[78],"Our":[79],"best":[80],"model,":[81],"which":[82],"incorporates":[83],"conditional":[84],"encodings,":[86],"significantly":[87],"improves":[88],"on":[90],"Audioset":[91],"ESC-50":[93],"compared":[94],"original":[97],"AST.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
