{"id":"https://openalex.org/W4406273203","doi":"https://doi.org/10.1109/icassp49660.2025.10887856","title":"AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder","display_name":"AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4406273203","doi":"https://doi.org/10.1109/icassp49660.2025.10887856"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2501.05332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021724743","display_name":"Samir Sadok","orcid":"https://orcid.org/0009-0007-5956-4133"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Samir Sadok","raw_affiliation_strings":["Inria at Univ. Grenoble Alpes,France","ROBOTLEARN - Vers des robots \u00e0 l\u2019intelligence sociale au travers de l\u2019apprentissage, de la perception et de la commande (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria at Univ. Grenoble Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"ROBOTLEARN - Vers des robots \u00e0 l\u2019intelligence sociale au travers de l\u2019apprentissage, de la perception et de la commande (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot - France)","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045593473","display_name":"Simon Leglaive","orcid":"https://orcid.org/0000-0002-8219-1298"},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Leglaive","raw_affiliation_strings":["CentraleSup&#x00E9;lec,France","CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSup&#x00E9;lec,France","institution_ids":["https://openalex.org/I4210107720"]},{"raw_affiliation_string":"CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["Univ. Grenoble Alpes,CNRS, Grenoble INP, GIPSA-Lab,France","Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology (46 avenue F\u00e9lix Viallet 38031 Grenoble Cedex 1 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes,CNRS, Grenoble INP, GIPSA-Lab,France","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I1294671590","https://openalex.org/I899635006","https://openalex.org/I106785703"]},{"raw_affiliation_string":"Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology (46 avenue F\u00e9lix Viallet 38031 Grenoble Cedex 1 - France)","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Richard","raw_affiliation_strings":["LTCI, T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de,Paris,France","LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T&#x00E9;l&#x00E9;com Paris, Institut Polytechnique de,Paris,France","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 PALAISEAU - France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["Inria at Univ. Grenoble Alpes,France","Inria Grenoble - Rh\u00f4ne-Alpes (Inovall\u00e9e\r\n655 avenue de l'Europe\r\n38330 Montbonnot - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inria at Univ. Grenoble Alpes,France","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348","https://openalex.org/I899635006"]},{"raw_affiliation_string":"Inria Grenoble - Rh\u00f4ne-Alpes (Inovall\u00e9e\r\n655 avenue de l'Europe\r\n38330 Montbonnot - France)","institution_ids":["https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1999,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.929073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9950000047683716,"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":0.9463000297546387,"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/speech-recognition","display_name":"Speech recognition","score":0.7780495882034302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7375146150588989},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6503046154975891},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.566650927066803},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4977893829345703},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47290122509002686},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4475022554397583},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4435613453388214},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4209243059158325},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41380977630615234},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4133770167827606},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.394069105386734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3268131613731384},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.13091713190078735},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09489789605140686},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.08424851298332214}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7780495882034302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7375146150588989},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6503046154975891},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.566650927066803},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4977893829345703},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47290122509002686},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4475022554397583},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4435613453388214},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4209243059158325},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41380977630615234},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4133770167827606},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.394069105386734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3268131613731384},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.13091713190078735},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09489789605140686},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.08424851298332214},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2501.05332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05332","pdf_url":"https://arxiv.org/pdf/2501.05332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":null},{"id":"pmh:oai:HAL:hal-04891286v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04891286","pdf_url":"https://hal.science/hal-04891286v1/document","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2025 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2025, Hyderabad, India. pp.1-5","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2501.05332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.05332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.05332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.05332","pdf_url":"https://arxiv.org/pdf/2501.05332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":null},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3110635976","display_name":null,"funder_award_id":"ANR-23-CE23-0009","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406273203.pdf","grobid_xml":"https://content.openalex.org/works/W4406273203.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1975079546","https://openalex.org/W2022554507","https://openalex.org/W2032026410","https://openalex.org/W2088432713","https://openalex.org/W2109114466","https://openalex.org/W2116428736","https://openalex.org/W2118774185","https://openalex.org/W2141998673","https://openalex.org/W2150980750","https://openalex.org/W2152205330","https://openalex.org/W2164764235","https://openalex.org/W2403891086","https://openalex.org/W2428180336","https://openalex.org/W2471520273","https://openalex.org/W2752796333","https://openalex.org/W2952218014","https://openalex.org/W2962788625","https://openalex.org/W2962866891","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3024869864","https://openalex.org/W3094502228","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3140429000","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W3215615641","https://openalex.org/W4225302959","https://openalex.org/W4297841766","https://openalex.org/W4307323391","https://openalex.org/W4313156423","https://openalex.org/W4372260337","https://openalex.org/W4385484923","https://openalex.org/W4386076005","https://openalex.org/W4387865047","https://openalex.org/W6739901393","https://openalex.org/W6757632829","https://openalex.org/W6757817989","https://openalex.org/W6762931180","https://openalex.org/W6777776875","https://openalex.org/W6783867762","https://openalex.org/W6802983977"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W1976952689","https://openalex.org/W1842536210","https://openalex.org/W2070982348","https://openalex.org/W1984921740","https://openalex.org/W2496295964","https://openalex.org/W1572861854","https://openalex.org/W2539491809","https://openalex.org/W2336887028","https://openalex.org/W2020464095"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"AnCoGen,":[3],"a":[4,9,23],"novel":[5],"method":[6],"that":[7],"leverages":[8],"masked":[10],"autoencoder":[11],"to":[12],"unify":[13],"the":[14,60,69],"analysis,":[15],"control,":[16],"and":[17,43,55,80,84],"generation":[18],"of":[19,59,71],"speech":[20,29,51,62,74,81],"signals":[21],"within":[22],"single":[24],"model.":[25],"AnCoGen":[26,72],"can":[27,49],"analyze":[28],"by":[30,63],"estimating":[31],"key":[32],"attributes,":[33],"such":[34],"as":[35],"speaker":[36],"identity,":[37],"pitch,":[38],"content,":[39],"loudness,":[40],"signal-to-noise":[41],"ratio,":[42],"clarity":[44],"index.":[45],"In":[46],"addition,":[47],"it":[48],"generate":[50],"from":[52],"these":[53],"attributes":[54],"allow":[56],"precise":[57],"control":[58],"synthesized":[61],"modifying":[64],"them.":[65],"Extensive":[66],"experiments":[67],"demonstrated":[68],"effectiveness":[70],"across":[73],"analysis-resynthesis,":[75],"pitch":[76,78],"estimation,":[77],"modification,":[79],"enhancement.":[82],"Code":[83],"audio":[85],"examples":[86],"are":[87],"available":[88],"online<sup":[89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-14T07:44:22.658603","created_date":"2025-01-11T00:00:00"}
