{"id":"https://openalex.org/W7150930724","doi":"https://doi.org/10.1145/3793853.3799811","title":"Audio Made Simple: A Modern Framework for Audio Processing","display_name":"Audio Made Simple: A Modern Framework for Audio Processing","publication_year":2026,"publication_date":"2026-04-04","ids":{"openalex":"https://openalex.org/W7150930724","doi":"https://doi.org/10.1145/3793853.3799811"},"language":null,"primary_location":{"id":"doi:10.1145/3793853.3799811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793853.3799811","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Systems Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793853.3799811","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002463407","display_name":"Jack Geraghty","orcid":null},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Jack Geraghty","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-5544-9484","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088174565","display_name":"Fatemeh Golpayegani","orcid":"https://orcid.org/0000-0002-3712-6550"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Fatemeh Golpayegani","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0002-3712-6550","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008608844","display_name":"Andrew Hines","orcid":"https://orcid.org/0000-0001-9636-2556"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Andrew Hines","raw_affiliation_strings":["School of Computer Science, University College Dublin, Dublin, Dublin, Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9636-2556","affiliations":[{"raw_affiliation_string":"School of Computer Science, University College Dublin, Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7930999994277954,"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":0.7930999994277954,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.01489999983459711,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.01269999984651804,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6391000151634216},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.6144000291824341},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49619999527931213},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3718999922275543},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.36410000920295715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.6144000291824341},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49619999527931213},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.36410000920295715},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.3328999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3294000029563904},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.28610000014305115},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3793853.3799811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793853.3799811","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Systems Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3793853.3799811","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793853.3799811","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Multimedia Systems Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2191779130","https://openalex.org/W4401516066"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"AudioSamples,":[3],"an":[4],"audio":[5,10,69],"processing":[6,76],"system":[7],"that":[8],"treats":[9],"as":[11,18,38],"a":[12],"first-class":[13],"data":[14],"type":[15],"rather":[16],"than":[17],"generic":[19],"numerical":[20],"arrays":[21],"accompanied":[22],"by":[23,62],"externally":[24],"managed":[25],"metadata.":[26],"In":[27],"many":[28],"existing":[29],"libraries,":[30],"researchers":[31],"must":[32],"manually":[33],"propagate":[34],"sampling":[35],"parameters":[36],"such":[37],"sample":[39],"rate,":[40],"channel":[41],"layout,":[42],"and":[43,54,71,81],"format":[44],"across":[45,75],"function":[46],"calls,":[47],"introducing":[48],"cognitive":[49],"overhead,":[50],"silent":[51],"error":[52],"modes,":[53],"reproducibility":[55],"risks.":[56],"AudioSamples":[57],"eliminates":[58],"this":[59],"coordination":[60],"burden":[61],"embedding":[63],"semantic":[64],"properties":[65],"directly":[66],"within":[67],"the":[68],"object":[70],"automatically":[72],"preserving":[73],"them":[74],"pipelines,":[77],"while":[78],"requiring":[79],"explicit":[80],"well-defined":[82],"conversions":[83],"when":[84],"semantics":[85],"change.":[86]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-07T00:00:00"}