{"id":"https://openalex.org/W4417402884","doi":"https://doi.org/10.1109/is264627.2025.11284585","title":"Toward Multimodal Audio Interfaces in Educational Music Production: A Microcontroller-Based Embedded System with Voice and Facial Control","display_name":"Toward Multimodal Audio Interfaces in Educational Music Production: A Microcontroller-Based Embedded System with Voice and Facial Control","publication_year":2025,"publication_date":"2025-10-29","ids":{"openalex":"https://openalex.org/W4417402884","doi":"https://doi.org/10.1109/is264627.2025.11284585"},"language":null,"primary_location":{"id":"doi:10.1109/is264627.2025.11284585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is264627.2025.11284585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 6th 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/A5106207536","display_name":"Pietro Buccellato","orcid":null},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Pietro Buccellato","raw_affiliation_strings":["Politecnico di Torino,Dep. of Electronics and Telecommunications,Turin,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Dep. of Electronics and Telecommunications,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062230069","display_name":"Cristina Rottondi","orcid":"https://orcid.org/0000-0002-9867-1093"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristina Rottondi","raw_affiliation_strings":["Politecnico di Torino,Dep. of Electronics and Telecommunications,Turin,Italy"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino,Dep. of Electronics and Telecommunications,Turin,Italy","institution_ids":["https://openalex.org/I177477856"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5106207536"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44245718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.17309999465942383,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.17309999465942383,"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/T11309","display_name":"Music and Audio Processing","score":0.08590000122785568,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.07559999823570251,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/interface","display_name":"Interface (matter)","score":0.6169999837875366},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.5121999979019165},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.45579999685287476},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.4242999851703644},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.383899986743927},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.35440000891685486},{"id":"https://openalex.org/keywords/stm32","display_name":"STM32","score":0.3441999852657318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7214999794960022},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.6169999837875366},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.5121999979019165},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.45899999141693115},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4020000100135803},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.35440000891685486},{"id":"https://openalex.org/C2779096738","wikidata":"https://www.wikidata.org/wiki/Q7394773","display_name":"STM32","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.3188999891281128},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.31529998779296875},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.29190000891685486},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2671000063419342}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/is264627.2025.11284585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is264627.2025.11284585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 6th International Symposium on the Internet of Sounds (IS2)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2611658824","https://openalex.org/W2737382791","https://openalex.org/W2795679027","https://openalex.org/W2909713066","https://openalex.org/W2971921316","https://openalex.org/W2990609012","https://openalex.org/W3112225120","https://openalex.org/W3136974624","https://openalex.org/W3161801295","https://openalex.org/W4289262380","https://openalex.org/W4296306264","https://openalex.org/W4389140175","https://openalex.org/W4396833058","https://openalex.org/W4396929191","https://openalex.org/W4403045847"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"interaction":[1,41],"represents":[2],"a":[3,29,73,99,108],"promising":[4,162],"direction":[5],"to":[6,34,98,123,146],"enhance":[7],"accessibility":[8],"and":[9,25,72,90,157],"inclusivity":[10],"in":[11,171],"Educational":[12],"Music":[13],"Production":[14],"(EMP)":[15],"environments.":[16],"This":[17],"work":[18],"reports":[19],"on":[20,78],"the":[21,60,84,104,121,134,148,151,166],"ongoing":[22],"design,":[23],"development,":[24],"feasibility":[26],"evaluation":[27,75,140],"of":[28,49,150],"microcontroller-based":[30],"embedded":[31],"system":[32,105],"designed":[33],"extend":[35],"standard":[36,69,135],"audio":[37,65,70,86],"interfaces":[38],"with":[39,141],"multimodal":[40,152],"capabilities.":[42],"The":[43],"proposed":[44],"solution":[45],"is":[46],"architecturally":[47],"composed":[48],"two":[50],"main":[51],"elements:":[52],"an":[53,79,112],"external":[54],"stereo":[55],"Analog-to-Digital":[56],"Converter":[57],"(ADC),":[58],"specifically":[59],"PCM1803AEVM,":[61],"which":[62,82,119],"digitizes":[63],"analog":[64],"signals":[66],"originating":[67],"from":[68],"interfaces;":[71],"NUCLEO-H723ZG":[74],"board,":[76],"based":[77],"STM32":[80],"microcontroller,":[81],"receives":[83],"digital":[85],"stream,":[87],"manages":[88],"buffering,":[89],"enables":[91],"data":[92],"transmission":[93],"over":[94],"Ethernet.":[95],"Once":[96],"connected":[97],"Local":[100],"Area":[101],"Network":[102],"(LAN),":[103],"operates":[106],"as":[107],"self-contained":[109],"server,":[110],"hosting":[111],"onboard,":[113],"browser-accessible":[114],"Web":[115],"Audio":[116],"Interface":[117],"(WAI)":[118],"allows":[120],"user":[122],"perform":[124],"core":[125],"production":[126],"tasks":[127],"through":[128],"voice":[129],"or":[130],"facial":[131,158],"commands,":[132],"besides":[133],"manual":[136],"ones.":[137],"A":[138],"functional":[139],"six":[142],"users":[143],"was":[144],"conducted":[145],"assess":[147],"accuracy":[149],"commands":[153],"across":[154],"diverse":[155],"vocal":[156],"profiles.":[159],"Results":[160],"indicate":[161],"recognition":[163],"accuracy,":[164],"supporting":[165],"case":[167],"for":[168],"further":[169],"validation":[170],"representative":[172],"EMP":[173],"scenarios.":[174]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-16T00:00:00"}