{"id":"https://openalex.org/W2157423596","doi":"https://doi.org/10.1186/s13636-014-0043-4","title":"The self-taught vocal interface","display_name":"The self-taught vocal interface","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2157423596","doi":"https://doi.org/10.1186/s13636-014-0043-4","mag":"2157423596"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-014-0043-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-014-0043-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0043-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0043-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056687428","display_name":"Bart Ons","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Bart Ons","raw_affiliation_strings":["Department ESAT-PSI, KU Leuven, Kasteelpark 10, Leuven, 3001, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ESAT-PSI, KU Leuven, Kasteelpark 10, Leuven, 3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109012430","display_name":"Jort F. Gemmeke","orcid":null},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jort F Gemmeke","raw_affiliation_strings":["Department ESAT-PSI, KU Leuven, Kasteelpark 10, Leuven, 3001, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ESAT-PSI, KU Leuven, Kasteelpark 10, Leuven, 3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["Department ESAT-PSI, KU Leuven, Kasteelpark 10, Leuven, 3001, Belgium"],"affiliations":[{"raw_affiliation_string":"Department ESAT-PSI, KU Leuven, Kasteelpark 10, Leuven, 3001, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5056687428"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.2723,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.85910199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2014","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech 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/T11309","display_name":"Music 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7980246543884277},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.6463522911071777},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6107924580574036},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6025131940841675},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.5723528265953064},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5433249473571777},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4550642967224121},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4314800798892975},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4258577525615692},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4240306615829468},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3763262927532196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3621867895126343},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.29986411333084106},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.20680910348892212},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.16766470670700073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7980246543884277},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.6463522911071777},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6107924580574036},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6025131940841675},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.5723528265953064},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5433249473571777},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4550642967224121},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4314800798892975},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4258577525615692},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4240306615829468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3763262927532196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3621867895126343},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29986411333084106},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.20680910348892212},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.16766470670700073},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-014-0043-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-014-0043-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0043-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/476934","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/476934","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech and Music Processing, vol. 43 (1), Art.No. ARTN 43, (1-16)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1186/s13636-014-0043-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-014-0043-4","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-014-0043-4","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2157423596.pdf","grobid_xml":"https://content.openalex.org/works/W2157423596.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W73629841","https://openalex.org/W83612550","https://openalex.org/W115171545","https://openalex.org/W121657759","https://openalex.org/W189630165","https://openalex.org/W203516808","https://openalex.org/W560739676","https://openalex.org/W1246381107","https://openalex.org/W1540882196","https://openalex.org/W1660019029","https://openalex.org/W1902027874","https://openalex.org/W1988871841","https://openalex.org/W1998988061","https://openalex.org/W2005243033","https://openalex.org/W2005358137","https://openalex.org/W2017977879","https://openalex.org/W2024081693","https://openalex.org/W2036932920","https://openalex.org/W2092881279","https://openalex.org/W2095935433","https://openalex.org/W2108919995","https://openalex.org/W2129674987","https://openalex.org/W2148154194","https://openalex.org/W2165108269","https://openalex.org/W2179211806","https://openalex.org/W2251514074","https://openalex.org/W2290004804","https://openalex.org/W2293401412","https://openalex.org/W2398131491","https://openalex.org/W2401439450","https://openalex.org/W2403712216","https://openalex.org/W2404400936","https://openalex.org/W2503460994","https://openalex.org/W2519992588","https://openalex.org/W6826952947"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W4231274751","https://openalex.org/W4389670110","https://openalex.org/W2187546663","https://openalex.org/W2429057255","https://openalex.org/W148745890","https://openalex.org/W2611942503","https://openalex.org/W2154063878"],"abstract_inverted_index":{"Speech":[0],"technology":[1],"is":[2],"firmly":[3],"rooted":[4],"in":[5,10,133,186],"daily":[6],"life,":[7],"most":[8],"notably":[9],"command-and-control":[11],"(C&C)":[12],"applications.":[13],"C&C":[14],"usability":[15],"downgrades":[16],"quickly,":[17],"however,":[18],"when":[19],"used":[20],"by":[21,51],"people":[22,162],"with":[23,130,144,163],"non-standard":[24,49],"speech.":[25,108],"We":[26],"pursue":[27],"a":[28,76,81,117,121,134,145,167,177],"fully":[29],"adaptive":[30],"vocal":[31],"user":[32],"interface":[33],"(VUI)":[34],"which":[35,126],"can":[36],"learn":[37],"both":[38],"vocabulary":[39],"and":[40,93,99,102,182],"grammar":[41],"directly":[42],"from":[43,55],"interaction":[44],"examples,":[45],"achieving":[46],"robustness":[47],"against":[48],"speech":[50,129,165],"building":[52],"up":[53],"models":[54],"scratch.":[56],"This":[57],"approach":[58],"raises":[59],"feasibility":[60,115],"concerns":[61],"on":[62,84,106,120,148],"the":[63,114,174],"amount":[64],"of":[65,116,176],"training":[66],"material":[67],"required":[68],"to":[69,89],"yield":[70],"an":[71],"acceptable":[72],"recognition":[73,159],"accuracy.":[74],"In":[75,109],"previous":[77],"work,":[78,111],"we":[79,112,139,172],"proposed":[80],"VUI":[82,119],"based":[83,147],"non-negative":[85],"matrix":[86],"factorisation":[87],"(NMF)":[88],"find":[90],"recurrent":[91],"acoustic":[92],"semantic":[94,179],"patterns":[95],"comprising":[96],"spoken":[97],"commands":[98,132],"device-specific":[100],"actions,":[101],"showed":[103],"its":[104,184],"effectiveness":[105,185],"unimpaired":[107],"this":[110],"evaluate":[113],"self-taught":[118],"new":[122],"database":[123],"called":[124],"domotica-3,":[125],"contains":[127],"dysarthric":[128,164],"typical":[131],"home":[135],"automation":[136],"setting.":[137],"Additionally,":[138],"compare":[140],"our":[141,154],"NMF-based":[142,155],"system":[143,146],"Gaussian":[149],"mixtures.":[150],"The":[151],"evaluation":[152],"favours":[153],"approach,":[156],"yielding":[157],"feasible":[158],"accuracies":[160],"for":[161],"after":[166],"few":[168],"learning":[169],"examples.":[170],"Finally,":[171],"propose":[173],"use":[175],"multi-layered":[178],"frame":[180],"structure":[181],"demonstrate":[183],"boosting":[187],"overall":[188],"performance.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}