{"id":"https://openalex.org/W4403182560","doi":"https://doi.org/10.1109/is262782.2024.10704099","title":"ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications","display_name":"ANIRA: An Architecture for Neural Network Inference in Real-Time Audio Applications","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4403182560","doi":"https://doi.org/10.1109/is262782.2024.10704099"},"language":"en","primary_location":{"id":"doi:10.1109/is262782.2024.10704099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.12665","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107806588","display_name":"Valentin Ackva","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Valentin Ackva","raw_affiliation_strings":["Audio Communication Group, Technische Universität Berlin,Berlin,Germany"],"affiliations":[{"raw_affiliation_string":"Audio Communication Group, Technische Universität Berlin,Berlin,Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113420984","display_name":"Fares Schulz","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fares Schulz","raw_affiliation_strings":["Audio Communication Group, Technische Universität Berlin,Berlin,Germany"],"affiliations":[{"raw_affiliation_string":"Audio Communication Group, Technische Universität Berlin,Berlin,Germany","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107806588"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":1.42500853,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72349762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T11349","display_name":"Music Technology and Sound Studies","score":0.9959999918937683,"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":0.9952999949455261,"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":0.7655124068260193},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6811485290527344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6168975234031677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5515331625938416},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5107245445251465},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3478587567806244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3376634418964386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30074578523635864},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2251489758491516},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1656540036201477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655124068260193},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6811485290527344},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6168975234031677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5515331625938416},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5107245445251465},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3478587567806244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3376634418964386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30074578523635864},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2251489758491516},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1656540036201477},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/is262782.2024.10704099","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 5th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.12665","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12665","pdf_url":"https://arxiv.org/pdf/2506.12665","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:2506.12665","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12665","pdf_url":"https://arxiv.org/pdf/2506.12665","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W562242262","https://openalex.org/W1951724000","https://openalex.org/W2121044470","https://openalex.org/W2519091744","https://openalex.org/W2526050071","https://openalex.org/W2952537531","https://openalex.org/W3000389243","https://openalex.org/W3000751478","https://openalex.org/W4225281045","https://openalex.org/W4281785064","https://openalex.org/W4287124627","https://openalex.org/W4309117899","https://openalex.org/W4381573670","https://openalex.org/W4389302098","https://openalex.org/W4399554262","https://openalex.org/W4403182560","https://openalex.org/W6639560864","https://openalex.org/W6713134421","https://openalex.org/W6730800615","https://openalex.org/W6751512325","https://openalex.org/W6764289567","https://openalex.org/W6766978945","https://openalex.org/W6840348479"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4321636575","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W2045526782","https://openalex.org/W2741131631","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Numerous":[0],"tools":[1],"for":[2,97,126,148],"neural":[3,37,94],"network":[4,38,95],"inference":[5,53,64],"are":[6,101],"currently":[7],"available,":[8],"yet":[9],"many":[10],"do":[11],"not":[12],"meet":[13],"the":[14,63,66,115,132,140,152],"requirements":[15],"of":[16,36,117,165],"real-time":[17,56,166],"audio":[18,67,98],"applications.":[19],"In":[20],"response,":[21],"we":[22],"introduce":[23],"anira,":[24],"an":[25],"efficient":[26],"cross-platform":[27],"library.":[28],"To":[29],"ensure":[30,87],"compatibility":[31],"with":[32],"a":[33,70,88,162],"broad":[34],"range":[35],"architectures":[39,96],"and":[40,47,80],"frameworks,":[41],"anira":[42,59],"supports":[43],"ONNX":[44,129],"Runtime,":[45],"LibTorch,":[46],"TensorFlow":[48],"Lite":[49],"as":[50],"backends.":[51],"Each":[52],"engine":[54],"exhibits":[55,131],"violations,":[57],"which":[58],"mitigates":[60],"by":[61],"decoupling":[62],"from":[65],"callback":[68],"to":[69,86,104,113],"static":[71],"thread":[72],"pool.":[73],"The":[74,122],"library":[75],"incorporates":[76],"built-in":[77],"latency":[78],"management":[79],"extensive":[81],"benchmarking":[82,105],"capabilities,":[83],"both":[84],"crucial":[85],"continuous":[89],"signal":[90],"flow.":[91],"Three":[92],"different":[93],"effect":[99],"emulation":[100],"then":[102],"subjected":[103],"across":[106],"various":[107,118],"configurations.":[108],"Statistical":[109],"modeling":[110],"is":[111],"employed":[112],"identify":[114],"influence":[116],"factors":[119],"on":[120],"performance.":[121,142],"findings":[123],"indicate":[124,146],"that":[125,147],"stateless":[127],"models,":[128,137],"Runtime":[130],"lowest":[133],"runtimes.":[134],"For":[135],"stateful":[136],"LibTorch":[138],"demonstrates":[139],"fastest":[141],"Our":[143],"results":[144],"also":[145],"certain":[149],"model-engine":[150],"combinations,":[151],"initial":[153],"inferences":[154,160],"take":[155],"longer,":[156],"particularly":[157],"when":[158],"these":[159],"exhibit":[161],"higher":[163],"incidence":[164],"violations.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}