{"id":"https://openalex.org/W3016077835","doi":"https://doi.org/10.1109/icassp40776.2020.9053006","title":"Neutral to Lombard Speech Conversion with Deep Learning","display_name":"Neutral to Lombard Speech Conversion with Deep Learning","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016077835","doi":"https://doi.org/10.1109/icassp40776.2020.9053006","mag":"3016077835"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021835215","display_name":"Enguerrand Gentet","orcid":null},"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":"Enguerrand Gentet","raw_affiliation_strings":["LTCI, 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, 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/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010434831","display_name":"Bertrand David","orcid":"https://orcid.org/0000-0002-5520-8613"},"institutions":[{"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":"Bertrand David","raw_affiliation_strings":["LTCI, Institut Polytechnique de Paris, France","SICAL - Situated Interaction, Collaboration, Adaptation and Learning (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"SICAL - Situated Interaction, Collaboration, Adaptation and Learning (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085282712","display_name":"S\u00e9bastien Denjean","orcid":"https://orcid.org/0000-0002-1476-949X"},"institutions":[{"id":"https://openalex.org/I268709337","display_name":"PSA Peugeot Citro\u00ebn (France)","ror":"https://ror.org/04zgvy449","country_code":"FR","type":"company","lineage":["https://openalex.org/I268709337"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sebastien Denjean","raw_affiliation_strings":["Groupe PSA, Chemin de Gisy, France","PSA Peugeot Citro\u00ebn (Centre Technique de Velizy, Route de Gisy, 78 943 V\u00e9lizy-Villacoublay - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Groupe PSA, Chemin de Gisy, France","institution_ids":["https://openalex.org/I268709337"]},{"raw_affiliation_string":"PSA Peugeot Citro\u00ebn (Centre Technique de Velizy, Route de Gisy, 78 943 V\u00e9lizy-Villacoublay - France)","institution_ids":["https://openalex.org/I268709337"]}]},{"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":"Gael Richard","raw_affiliation_strings":["LTCI, Institut Polytechnique de Paris, France","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Institut Polytechnique de Paris, France","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030975522","display_name":"Vincent Roussarie","orcid":null},"institutions":[{"id":"https://openalex.org/I268709337","display_name":"PSA Peugeot Citro\u00ebn (France)","ror":"https://ror.org/04zgvy449","country_code":"FR","type":"company","lineage":["https://openalex.org/I268709337"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Roussarie","raw_affiliation_strings":["Groupe PSA, Chemin de Gisy, France","Equipe Perception et cognition musicales (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Groupe PSA, Chemin de Gisy, France","institution_ids":["https://openalex.org/I268709337"]},{"raw_affiliation_string":"Equipe Perception et cognition musicales (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3286,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.45168099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"7739","last_page":"7743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7540557384490967},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6779903769493103},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.5743821859359741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5695896148681641},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5500997304916382},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5045899152755737},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49729397892951965},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48954519629478455},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4840802252292633},{"id":"https://openalex.org/keywords/continuous-wavelet-transform","display_name":"Continuous wavelet transform","score":0.47469156980514526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4020507037639618},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.22885185480117798},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09975451231002808}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7540557384490967},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6779903769493103},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.5743821859359741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5695896148681641},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5500997304916382},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5045899152755737},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49729397892951965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48954519629478455},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4840802252292633},{"id":"https://openalex.org/C95722684","wikidata":"https://www.wikidata.org/wiki/Q2622756","display_name":"Continuous wavelet transform","level":5,"score":0.47469156980514526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4020507037639618},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.22885185480117798},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09975451231002808},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02713204v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02713204","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020, Barcelona, France. pp.7739-7743, ⟨10.1109/ICASSP40776.2020.9053006⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1540083112","https://openalex.org/W1588037970","https://openalex.org/W2034139177","https://openalex.org/W2077801020","https://openalex.org/W2077809714","https://openalex.org/W2113395503","https://openalex.org/W2131062138","https://openalex.org/W2154920538","https://openalex.org/W2161736993","https://openalex.org/W2185573909","https://openalex.org/W2404098313","https://openalex.org/W2517513811","https://openalex.org/W2556522401","https://openalex.org/W2611963065","https://openalex.org/W2747057337","https://openalex.org/W2810311710","https://openalex.org/W2911412811","https://openalex.org/W2936173958","https://openalex.org/W2963815651","https://openalex.org/W6713590759","https://openalex.org/W6730169791"],"related_works":["https://openalex.org/W2373349805","https://openalex.org/W2077021924","https://openalex.org/W4309182840","https://openalex.org/W3197430789","https://openalex.org/W2611150080","https://openalex.org/W2375973715","https://openalex.org/W2129884646","https://openalex.org/W2094847008","https://openalex.org/W3011345265","https://openalex.org/W1518678555"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"several":[5],"approaches":[6],"for":[7,81],"neutral":[8],"to":[9,49],"Lombard":[10],"speech":[11,60],"conversion.":[12],"We":[13,36],"study":[14],"in":[15,73],"particular":[16,74],"the":[17,39,55,75,78,82],"influence":[18],"of":[19,54,68,77],"different":[20,56],"recurrent":[21],"neural":[22],"network":[23],"architectures":[24],"where":[25],"their":[26],"main":[27],"hyper-parameters":[28],"are":[29,64],"carefully":[30],"selected":[31],"using":[32],"a":[33,45],"bandit-based":[34],"approach.":[35],"also":[37],"apply":[38],"Continuous":[40],"Wavelet":[41],"Transform":[42],"(CWT)":[43],"as":[44],"multi-resolution":[46],"analysis":[47],"framework":[48],"better":[50],"model":[51],"temporal":[52],"dependencies":[53],"features":[57],"selected.":[58],"The":[59],"conversion":[61],"results":[62],"obtained":[63],"validated":[65],"by":[66],"means":[67],"objective":[69],"evaluations":[70],"which":[71],"highlight":[72],"interest":[76],"wavelet":[79],"transform":[80],"learning":[83],"process.":[84]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}