{"id":"https://openalex.org/W4412398327","doi":"https://doi.org/10.1186/s13636-025-00414-5","title":"Parameter optimisation for a physical model of the vocal system","display_name":"Parameter optimisation for a physical model of the vocal system","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4412398327","doi":"https://doi.org/10.1186/s13636-025-00414-5"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00414-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00414-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00414-5","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/s13636-025-00414-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059425661","display_name":"Mateo C\u00e1mara","orcid":"https://orcid.org/0000-0002-1055-6315"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Mateo C\u00e1mara","raw_affiliation_strings":["Grupo de Aplicaciones del Procesado de Se\u00f1al, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Information Processing and Telecommunications Center, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1055-6315","affiliations":[{"raw_affiliation_string":"Grupo de Aplicaciones del Procesado de Se\u00f1al, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Information Processing and Telecommunications Center, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038587924","display_name":"Jos\u00e9 Luis Blanco","orcid":null},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Luis Blanco","raw_affiliation_strings":["Grupo de Aplicaciones del Procesado de Se\u00f1al, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","Information Processing and Telecommunications Center, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grupo de Aplicaciones del Procesado de Se\u00f1al, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]},{"raw_affiliation_string":"Information Processing and Telecommunications Center, Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111403298","display_name":"Joshua D. Reiss","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joshua D. Reiss","raw_affiliation_strings":["Centre for Digital Music, Queen Mary University of London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059425661"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.8114,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9344195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2025","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":0.9995999932289124,"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":0.9995999932289124,"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":0.9988999962806702,"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":0.9987999796867371,"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":0.9151327013969421},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3966217339038849},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.34203672409057617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9151327013969421},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3966217339038849},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.34203672409057617}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00414-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00414-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00414-5","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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:doaj.org/article:c6c9924c3bbf4301b25a96cd1f2310fc","is_oa":true,"landing_page_url":"https://doaj.org/article/c6c9924c3bbf4301b25a96cd1f2310fc","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-15 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00414-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00414-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-025-00414-5","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":[],"awards":[{"id":"https://openalex.org/G2254750487","display_name":null,"funder_award_id":"PID2021-128469OB-I00","funder_id":"https://openalex.org/F4320326262","funder_display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a"},{"id":"https://openalex.org/G4090683949","display_name":null,"funder_award_id":"101003750","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"},{"id":"https://openalex.org/G6911004936","display_name":"INNOVATIVE DIGITAL SUSTAINABLE AGGREGATES SYSTEMS","funder_award_id":"101003750","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8729171197","display_name":null,"funder_award_id":"PID2021-128469OB-I00","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320326262","display_name":"Ministerio de Asuntos Econ\u00f3micos y Transformaci\u00f3n Digital, Gobierno de Espa\u00f1a","ror":"https://ror.org/03sv46s19"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412398327.pdf","grobid_xml":"https://content.openalex.org/works/W4412398327.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W46188241","https://openalex.org/W123135133","https://openalex.org/W623495177","https://openalex.org/W1499220978","https://openalex.org/W1503296932","https://openalex.org/W1728888090","https://openalex.org/W1965378753","https://openalex.org/W1970242389","https://openalex.org/W1971596446","https://openalex.org/W1977591085","https://openalex.org/W1993096868","https://openalex.org/W2006775235","https://openalex.org/W2025877346","https://openalex.org/W2026149420","https://openalex.org/W2035395798","https://openalex.org/W2054159638","https://openalex.org/W2118774185","https://openalex.org/W2123778414","https://openalex.org/W2183414650","https://openalex.org/W2194775991","https://openalex.org/W2322951925","https://openalex.org/W2791716806","https://openalex.org/W2883879995","https://openalex.org/W2896035909","https://openalex.org/W2972537746","https://openalex.org/W3037038648","https://openalex.org/W3094929307","https://openalex.org/W3197184958","https://openalex.org/W4220948221","https://openalex.org/W4245845544","https://openalex.org/W4294811280","https://openalex.org/W4392405784","https://openalex.org/W4400268566","https://openalex.org/W4404563387","https://openalex.org/W4408354665","https://openalex.org/W6600547436"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"study":[1],"explores":[2],"optimisation":[3,92],"techniques":[4,109],"for":[5,76,123,136],"refining":[6],"articulatory":[7,45,137],"parameters":[8],"in":[9,27,110,127],"the":[10,91,97,115],"Pink":[11],"Trombone,":[12],"a":[13,37,81,86,120,134],"simplified":[14],"physical":[15,128],"speech":[16,129],"synthesiser,":[17],"to":[18,43,60,66,89,100],"accurately":[19],"emulate":[20],"male":[21],"and":[22,33,40,80,143,147],"female":[23],"vocal":[24],"tract":[25],"characteristics":[26],"non-speech":[28],"sounds.":[29],"We":[30,70,113],"employ":[31],"black-box":[32],"grey-box":[34,72],"approaches,":[35],"leveraging":[36],"genetic":[38],"optimiser":[39],"Mel-spectrogram":[41],"representations":[42],"infer":[44],"configurations":[46],"from":[47],"human":[48,102],"recordings":[49],"via":[50],"direct":[51],"spectral":[52],"comparison.":[53],"Optimisation":[54],"is":[55],"performed":[56],"over":[57,107],"time":[58],"windows":[59],"ensure":[61],"temporal":[62],"coherence,":[63],"introducing":[64],"modifications":[65],"SOTA":[67],"objective":[68],"metrics.":[69],"integrate":[71],"strategies,":[73],"incorporating":[74],"pYIN":[75],"fundamental":[77],"frequency":[78],"estimation":[79],"ResNet-based":[82],"neural":[83,87],"network":[84],"as":[85],"codebook":[88],"enhance":[90],"process.":[93],"Our":[94],"findings":[95],"confirm":[96],"synthesiser\u2019s":[98],"ability":[99],"replicate":[101],"vocalisations,":[103],"achieving":[104],"superior":[105],"performance":[106],"existing":[108],"subjective":[111],"evaluations.":[112],"refined":[114],"perceptual":[116],"metric":[117],"ViSQOL,":[118],"providing":[119],"calibrated":[121],"framework":[122],"future":[124],"auditory":[125],"assessments":[126],"synthesis.":[130],"These":[131],"contributions":[132],"establish":[133],"methodology":[135],"parameter":[138],"estimation,":[139],"improving":[140],"synthesis":[141],"quality":[142],"expanding":[144],"vocalisation":[145],"modelling":[146],"analysis":[148],"applications.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}