{"id":"https://openalex.org/W2897248861","doi":"https://doi.org/10.1145/3277593.3277610","title":"Speech recognition and voice separation for the internet of things","display_name":"Speech recognition and voice separation for the internet of things","publication_year":2018,"publication_date":"2018-10-11","ids":{"openalex":"https://openalex.org/W2897248861","doi":"https://doi.org/10.1145/3277593.3277610","mag":"2897248861"},"language":"en","primary_location":{"id":"doi:10.1145/3277593.3277610","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3277593.3277610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on the Internet of Things","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/A5101457271","display_name":"Mohammad Hasanzadeh Mofrad","orcid":"https://orcid.org/0000-0003-4369-6928"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mohammad Hasanzadeh Mofrad","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088337929","display_name":"Daniel Moss\u00e9","orcid":"https://orcid.org/0000-0002-9508-9815"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Mosse","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101457271"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":1.4863,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.83882517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11447","display_name":"Blind Source Separation Techniques","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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6640405058860779},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6506638526916504},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5616776347160339},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4987008571624756},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.4980437755584717},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.47705498337745667},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.262320339679718},{"id":"https://openalex.org/keywords/internet-privacy","display_name":"Internet privacy","score":0.24399268627166748},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06334412097930908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6640405058860779},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6506638526916504},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5616776347160339},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4987008571624756},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.4980437755584717},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.47705498337745667},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.262320339679718},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.24399268627166748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06334412097930908}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3277593.3277610","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3277593.3277610","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th International Conference on the Internet of Things","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1515135833","https://openalex.org/W1971243715","https://openalex.org/W1975301756","https://openalex.org/W2019269619","https://openalex.org/W2034940213","https://openalex.org/W2036107592","https://openalex.org/W2064675550","https://openalex.org/W2080213370","https://openalex.org/W2099741732","https://openalex.org/W2111619626","https://openalex.org/W2112274848","https://openalex.org/W2142638745","https://openalex.org/W2147757279","https://openalex.org/W2248617261","https://openalex.org/W2293829681","https://openalex.org/W2403583711","https://openalex.org/W2766700633","https://openalex.org/W6746451879"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149","https://openalex.org/W2368768466"],"abstract_inverted_index":{"Internet-connected":[0],"home":[1,75],"automation":[2],"devices":[3,33,91],"like":[4,65],"Amazon":[5,66],"Echo,":[6],"Nest":[7],"Thermostat":[8],"and":[9,26,49,68,137,146,151,182,190],"smart":[10],"TVs":[11],"are":[12,84,130,172,185],"riding":[13],"the":[14,17,45,60,105,159,165,205,215],"wave":[15],"of":[16,19,59,79,89,127,161,167,207],"Internet":[18],"Things":[20],"(IoT).":[21],"The":[22,125],"most":[23],"intuitive,":[24],"natural":[25],"efficient":[27],"way":[28],"to":[29,47,53,157,174,177,187,211,214],"communicate":[30],"with":[31,37],"these":[32,90],"is":[34,92,117],"through":[35],"talking":[36],"them":[38],"(via":[39],"voice":[40,98,162,196,223],"commands).":[41],"Speech":[42],"recognition":[43],"provides":[44],"medium":[46],"process":[48,209],"convert":[50],"spoken":[51],"language":[52],"plain":[54],"text":[55],"for":[56,74,222],"further":[57],"use":[58],"system.":[61],"Current":[62],"personal":[63],"assistants":[64],"Echo":[67],"Google":[69,147],"Home":[70],"have":[71],"been":[72],"designed":[73],"automation,":[76],"impacting":[77],"billions":[78],"people's":[80],"lives;":[81],"yet,":[82],"they":[83,94],"not":[85,220],"customizable.":[86],"Another":[87],"limitation":[88],"that":[93,114,202],"cannot":[95],"recognize":[96],"concurrent":[97],"commands":[99,176,184],"issued":[100],"by":[101],"two":[102,170],"persons":[103],"at":[104],"same":[106],"time.":[107],"We":[108],"tackle":[109],"this":[110,128],"last":[111],"challenge,":[112],"given":[113],"often":[115],"there":[116],"more":[118],"than":[119],"one":[120],"person":[121],"in":[122,164],"each":[123],"room.":[124],"contributions":[126],"paper":[129],"twofold:":[131],"(1)":[132],"we":[133,153,203],"build":[134],"an":[135],"inexpensive":[136],"customizable":[138],"voice-enabled":[139,179],"IoT":[140,168,180],"prototype":[141],"using":[142],"Raspberry":[143],"Pi":[144],"motherboard":[145],"Cloud":[148],"speech-to-text":[149],"API":[150],"(2)":[152],"propose":[154],"a":[155,178],"method":[156],"solve":[158],"problem":[160],"separation":[163,197],"context":[166],"when":[169],"people":[171],"trying":[173],"send":[175],"device":[181],"both":[183],"required":[186],"be":[188],"processed":[189],"executed":[191],"simultaneously.":[192],"Using":[193],"our":[194,199],"proposed":[195],"approach,":[198],"results":[200],"showed":[201],"improved":[204],"accuracy":[206],"transcription":[208],"up":[210],"3%":[212],"compared":[213],"baseline":[216],"model":[217],"which":[218],"does":[219],"support":[221],"separation.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
