{"id":"https://openalex.org/W7208776296","doi":"https://doi.org/10.48550/arxiv.2609.03940","title":"Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations","display_name":"Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208776296","doi":"https://doi.org/10.48550/arxiv.2609.03940"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.03940","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03940","pdf_url":"https://arxiv.org/pdf/2609.03940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.03940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089632772","display_name":"Yoto Fujita","orcid":null,"observed_orcids":[]},"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/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"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"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fujita, Yoto","raw_affiliation_strings":["CentraleSup\u00e9lec , IETR (UMR CNRS 6164) , France","Univ. Grenoble Alpes , CNRS , Grenoble-INP , GIPSA-lab , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSup\u00e9lec , IETR (UMR CNRS 6164) , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210100151","https://openalex.org/I4210107720"]},{"raw_affiliation_string":"Univ. Grenoble Alpes , CNRS , Grenoble-INP , GIPSA-lab , France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045593473","display_name":"Simon Leglaive","orcid":"https://orcid.org/0000-0002-8219-1298","observed_orcids":["https://orcid.org/0000-0002-8219-1298"]},"institutions":[{"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/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"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":"Leglaive, Simon","raw_affiliation_strings":["CentraleSup\u00e9lec , IETR (UMR CNRS 6164) , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSup\u00e9lec , IETR (UMR CNRS 6164) , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210100151","https://openalex.org/I4210107720"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin B","orcid":"https://orcid.org/0000-0002-9214-8760","observed_orcids":["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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Girin, Laurent","raw_affiliation_strings":["Univ. Grenoble Alpes , CNRS , Grenoble-INP , GIPSA-lab , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes , CNRS , Grenoble-INP , GIPSA-lab , France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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":0.0,"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-enhancement","display_name":"speech enhancement","score":0.9779999852180481},{"id":"https://openalex.org/keywords/neural-audio-codecs","display_name":"neural audio codecs","score":0.8799999952316284},{"id":"https://openalex.org/keywords/iterative-decoding","display_name":"iterative decoding","score":0.6340000033378601},{"id":"https://openalex.org/keywords/conformers","display_name":"conformational isomers","score":0.5849999785423279},{"id":"https://openalex.org/keywords/computational-cost-trade-off","display_name":"computational cost trade-off","score":0.7009999752044678},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.6029999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411999702453613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7055000066757202},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42989999055862427},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3337000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.28700000047683716},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.2630999982357025},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2609.03940","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03940","pdf_url":"https://arxiv.org/pdf/2609.03940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05737791v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05737791v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IWAENC 2026 - 19th International Workshop on Acoustic Signal Enhancement (IWAENC), Sep 2026, Cremona, Italy","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2609.03940","doi":"https://doi.org/10.48550/arxiv.2609.03940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.03940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.03940","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03940","pdf_url":"https://arxiv.org/pdf/2609.03940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208776296.pdf","grobid_xml":"https://content.openalex.org/works/W7208776296.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416046971","https://openalex.org/W4408355354","https://openalex.org/W7164908909","https://openalex.org/W7202372921","https://openalex.org/W4414787333","https://openalex.org/W7167465441","https://openalex.org/W7155100118","https://openalex.org/W4414821099","https://openalex.org/W7126152220","https://openalex.org/W7127323749"],"abstract_inverted_index":{"Most":[0],"previous":[1],"work":[2],"on":[3,8,13,64],"speech":[4,46,70],"enhancement":[5],"(SE)":[6],"based":[7,63],"masked":[9,55,68],"generative":[10],"modeling":[11],"relied":[12],"discrete":[14],"token":[15],"representations":[16,35,75],"of":[17,36,45,67,76,84],"audio":[18,23],"signals,":[19],"obtained":[20],"using":[21,72,92],"neural":[22],"codecs":[24],"(NACs).":[25],"However,":[26],"a":[27,59,82,116],"recent":[28],"study":[29],"has":[30],"shown":[31],"that":[32,90,113],"continuous":[33,73],"latent":[34],"NACs":[37],"can":[38],"be":[39],"advantageous":[40],"for":[41,61],"SE":[42,57,62,120],"in":[43],"terms":[44],"quality":[47],"and":[48,105,122,127],"intelligibility.":[49],"In":[50,78],"this":[51],"work,":[52],"we":[53,80],"propose":[54],"autoregressive":[56],"(MARSE),":[58],"method":[60],"iterative":[65],"decoding":[66,86],"clean":[69],"frames":[71],"NAC":[74,101],"speech.":[77],"particular,":[79],"investigate":[81],"set":[83],"different":[85],"policies,":[87],"ceteris":[88],"paribus,":[89],"is,":[91],"the":[93,99,106],"same":[94,100,107],"DNN":[95],"(a":[96],"Conformer":[97],"model),":[98],"(the":[102],"DAC":[103],"codec)":[104],"training":[108],"setup.":[109],"The":[110],"results":[111],"show":[112],"MARSE":[114],"enables":[115],"flexible":[117],"trade-off":[118],"between":[119],"performance":[121],"computational":[123],"cost.":[124],"Audio":[125],"examples":[126],"code":[128],"are":[129],"available":[130],"online.":[131]},"counts_by_year":[],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2026-09-05T00:00:00"}