{"id":"https://openalex.org/W4403183448","doi":"https://doi.org/10.1109/is262782.2024.10704173","title":"TinyVocos: Neural Vocoders on MCUs","display_name":"TinyVocos: Neural Vocoders on MCUs","publication_year":2024,"publication_date":"2024-09-30","ids":{"openalex":"https://openalex.org/W4403183448","doi":"https://doi.org/10.1109/is262782.2024.10704173"},"language":"en","primary_location":{"id":"doi:10.1109/is262782.2024.10704173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704173","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107806709","display_name":"Stefano Ciapponi","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Stefano Ciapponi","raw_affiliation_strings":["Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler","University of Trento, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019442580","display_name":"Francesco Paissan","orcid":"https://orcid.org/0000-0002-5553-7935"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Paissan","raw_affiliation_strings":["Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler"],"affiliations":[{"raw_affiliation_string":"Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046416586","display_name":"Alberto Ancilotto","orcid":"https://orcid.org/0000-0002-1396-3709"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Ancilotto","raw_affiliation_strings":["Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler","University of Trento, Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068548938","display_name":"Elisabetta Farella","orcid":"https://orcid.org/0000-0001-9047-9868"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisabetta Farella","raw_affiliation_strings":["Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler"],"affiliations":[{"raw_affiliation_string":"Energy Efficient Embedded Digital Architectures, Fondazione Bruno Kessler","institution_ids":["https://openalex.org/I2277624104"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5107806709"],"corresponding_institution_ids":["https://openalex.org/I193223587","https://openalex.org/I2277624104"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76597759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"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/T10320","display_name":"Neural Networks and Applications","score":0.42829999327659607,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.42829999327659607,"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":0.6659360527992249},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46863675117492676},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35651886463165283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3513084650039673}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6659360527992249},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46863675117492676},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35651886463165283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3513084650039673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/is262782.2024.10704173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is262782.2024.10704173","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1789794644","https://openalex.org/W2152859600","https://openalex.org/W2559655401","https://openalex.org/W2593463961","https://openalex.org/W2791686384","https://openalex.org/W2890983311","https://openalex.org/W2913668833","https://openalex.org/W2914304175","https://openalex.org/W2962935966","https://openalex.org/W2963163009","https://openalex.org/W2963816101","https://openalex.org/W2972359262","https://openalex.org/W2999905431","https://openalex.org/W3010074503","https://openalex.org/W3036601975","https://openalex.org/W3037038648","https://openalex.org/W3047691788","https://openalex.org/W3096799113","https://openalex.org/W3147508412","https://openalex.org/W3161236344","https://openalex.org/W3197095449","https://openalex.org/W4205097469","https://openalex.org/W4206437029","https://openalex.org/W4210269029","https://openalex.org/W4210287297","https://openalex.org/W4212807739","https://openalex.org/W4224612669","https://openalex.org/W4230442869","https://openalex.org/W4282044900","https://openalex.org/W4323519173","https://openalex.org/W4390871989","https://openalex.org/W4395054510","https://openalex.org/W4402112510","https://openalex.org/W6638142982","https://openalex.org/W6732429163","https://openalex.org/W6733471323","https://openalex.org/W6736996214","https://openalex.org/W6755592152","https://openalex.org/W6767111847","https://openalex.org/W6773094808","https://openalex.org/W6773238774","https://openalex.org/W6779801287","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6805648192","https://openalex.org/W6810129404","https://openalex.org/W6846013124","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6849446024","https://openalex.org/W6851952482","https://openalex.org/W6853084291","https://openalex.org/W6853165267","https://openalex.org/W6853604381","https://openalex.org/W6855718144"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398","https://openalex.org/W2775347418"],"abstract_inverted_index":{"Neural":[0],"Vocoders":[1,12],"convert":[2],"time-frequency":[3],"representations,":[4],"such":[5],"as":[6],"mel-spectrograms,":[7],"into":[8],"corresponding":[9],"time":[10],"representations.":[11],"are":[13],"essential":[14],"for":[15,31,127],"generative":[16],"applications":[17,95],"in":[18,96],"audio":[19,130],"(e.g.":[20],"text-to-speech":[21],"and":[22,38,42,51,55,58,62,101,119,123],"text-to-audio).":[23],"This":[24],"paper":[25],"presents":[26],"a":[27,109,128],"scalable":[28],"vocoder":[29],"architecture":[30],"small-footprint":[32],"edge":[33,90],"devices,":[34,91],"inspired":[35],"by":[36],"Vocos":[37],"adapted":[39],"with":[40],"XiNets":[41],"PhiNets.":[43],"We":[44],"test":[45],"the":[46,71,82],"developed":[47],"model":[48,107],"capabilities":[49],"qualitatively":[50],"quantitatively":[52],"on":[53,65,74,88],"single-speaker":[54],"multi-speaker":[56],"datasets":[57],"benchmark":[59],"inference":[60],"speed":[61],"memory":[63],"consumption":[64,73],"four":[66],"microcontrollers.":[67],"Additionally,":[68],"we":[69],"study":[70],"power":[72],"an":[75],"ARM":[76],"Cortex-M7-powered":[77],"board.":[78],"Our":[79,105],"results":[80],"demonstrate":[81],"feasibility":[83],"of":[84,98,112,117,121],"deploying":[85],"neural":[86],"vocoders":[87],"resource-constrained":[89],"potentially":[92],"enabling":[93],"new":[94],"Internet":[97],"Sounds":[99],"(IoS)":[100],"Embedded":[102],"Audio":[103],"scenarios.":[104],"best-performing":[106],"achieves":[108],"MOS":[110],"score":[111],"3.95/5":[113],"while":[114],"utilizing":[115],"1.5MiB":[116],"FLASH":[118],"517KiB":[120],"RAM":[122],"consuming":[124],"252":[125],"mW":[126],"1s":[129],"clip":[131],"inference.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}