{"id":"https://openalex.org/W2746549158","doi":"https://doi.org/10.21437/interspeech.2017-804","title":"A Speaker Adaptive DNN Training Approach for Speaker-Independent Acoustic Inversion","display_name":"A Speaker Adaptive DNN Training Approach for Speaker-Independent Acoustic Inversion","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746549158","doi":"https://doi.org/10.21437/interspeech.2017-804","mag":"2746549158"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-804","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-02166128","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063165262","display_name":"Leonardo Badino","orcid":"https://orcid.org/0000-0001-7037-5914"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Leonardo Badino","raw_affiliation_strings":["IIT - Istituto Italiano di Tecnologia (Via Morego, 30 16163 Genova - Italy)"],"affiliations":[{"raw_affiliation_string":"IIT - Istituto Italiano di Tecnologia (Via Morego, 30 16163 Genova - Italy)","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074874504","display_name":"Luca Franceschi","orcid":"https://orcid.org/0000-0002-1810-1016"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["GB","IT"],"is_corresponding":false,"raw_author_name":"Luca Franceschi","raw_affiliation_strings":["Istituto Italiano di Tecnologia, Italy","University College London, UK"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063457506","display_name":"Raman Arora","orcid":"https://orcid.org/0000-0003-2002-3923"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raman Arora","raw_affiliation_strings":["Johns Hopkins University, MD,USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, MD,USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056775618","display_name":"Michele Donini","orcid":"https://orcid.org/0000-0002-9769-3899"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Michele Donini","raw_affiliation_strings":["Istituto Italiano di Tecnologia, Italy"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034260726","display_name":"Massimiliano Pontil","orcid":"https://orcid.org/0000-0001-9415-098X"},"institutions":[{"id":"https://openalex.org/I4210133681","display_name":"2iC (United Kingdom)","ror":"https://ror.org/03txtgw38","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210133681"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Massimiliano Pontil","raw_affiliation_strings":["Department of Computer Science (Egham, Surrey TW20 0EX - United Kingdom)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science (Egham, Surrey TW20 0EX - United Kingdom)","institution_ids":["https://openalex.org/I4210133681"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063165262"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":0.6229,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77260007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"984","last_page":"988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/T10860","display_name":"Speech and Audio Processing","score":0.9883000254631042,"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":0.72963947057724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6720393896102905},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5519716143608093},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5152971744537354},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.5131102800369263},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.509486734867096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4527651071548462},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.44952598214149475},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.43692561984062195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3716166615486145}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.72963947057724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6720393896102905},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5519716143608093},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5152971744537354},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.5131102800369263},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.509486734867096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4527651071548462},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.44952598214149475},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.43692561984062195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3716166615486145},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-804","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-804","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02166128v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02166128","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.984-988, ⟨10.21437/Interspeech.2017-804⟩","raw_type":"Conference papers"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10046566","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10046566/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In: Lacerda, F, (ed.) Proceedings of Interspeech 2017.  (pp. pp. 984-988).  International Speech Communication Association (ISCA): Stockholm, Sweden. (2017)     ","raw_type":"Proceedings paper"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02166128v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02166128","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.984-988, ⟨10.21437/Interspeech.2017-804⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W40881502","https://openalex.org/W201148316","https://openalex.org/W900447646","https://openalex.org/W1496997718","https://openalex.org/W1531883353","https://openalex.org/W1554663460","https://openalex.org/W1599512239","https://openalex.org/W1758409092","https://openalex.org/W1980837758","https://openalex.org/W1982854652","https://openalex.org/W1990394889","https://openalex.org/W2116082100","https://openalex.org/W2134539847","https://openalex.org/W2143104527","https://openalex.org/W2154074091","https://openalex.org/W2173020502","https://openalex.org/W2395955767","https://openalex.org/W2404570131","https://openalex.org/W2554146567","https://openalex.org/W2991037323","https://openalex.org/W4295292688","https://openalex.org/W4302557958","https://openalex.org/W4388297464"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"We":[0,142],"address":[1],"the":[2,40,59,68,83,146],"speaker-independent":[3,123],"acoustic":[4],"inversion":[5],"(AI)":[6],"problem,":[7],"also":[8],"referred":[9],"to":[10,24,92,128],"as":[11],"acoustic-to-articulatory":[12,107],"mapping.":[13],"The":[14,132,158],"scarce":[15],"availability":[16],"of":[17,34,43,61,70,134,148],"multi-speaker":[18],"articulatory":[19,41],"data":[20],"makes":[21],"it":[22,91],"difficult":[23],"learn":[25,103],"a":[26,31,51,111,121,139,169],"mapping":[27,108],"which":[28],"generalizes":[29],"from":[30,67,82],"limited":[32],"number":[33],"training":[35,63,100],"speakers":[36],"and":[37,89],"reliably":[38],"reconstructs":[39],"movements":[42],"unseen":[44],"speakers.":[45,78],"In":[46],"this":[47],"paper,":[48],"we":[49,102,118],"propose":[50],"Multi-task":[52],"Learning":[53],"(MTL)-based":[54],"approach":[55,80,88],"that":[56,73,125,162],"explicitly":[57],"separates":[58],"modeling":[60,69],"each":[62,105],"speaker":[64,176],"AI":[65,71],"peculiarities":[66],"characteristics":[72],"are":[74],"shared":[75],"by":[76,110,138],"all":[77,129],"Our":[79],"stems":[81],"well":[84],"known":[85],"Regularized":[86],"MTL":[87],"extends":[90],"feed-forward":[93],"deep":[94],"neural":[95],"networks":[96],"(DNNs).":[97],"Given":[98],"multiple":[99],"speakers,":[101],"for":[104,120],"an":[106,115],"represented":[109],"DNN.":[112,178],"Then,":[113],"through":[114],"iterative":[116],"procedure,":[117],"search":[119],"canonical":[122,165],"DNN":[124,166],"is":[126,136],"\"similar\"":[127],"speaker-dependent":[130],"DNNs.":[131],"degree":[133],"similarity":[135],"controlled":[137],"regularization":[140],"parameter.":[141],"report":[143],"experiments":[144],"on":[145],"University":[147],"Wisconsin":[149],"X-ray":[150],"Microbeam":[151],"Database":[152],"under":[153],"different":[154],"training/testing":[155],"experimental":[156],"settings.":[157],"results":[159],"obtained":[160],"indicate":[161],"our":[163],"MTL-trained":[164],"largely":[167],"outperforms":[168],"standardly":[170],"trained":[171],"(i.e.,":[172],"single":[173],"task":[174],"learning-based)":[175],"independent":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}