{"id":"https://openalex.org/W7148513141","doi":"https://doi.org/10.1109/asru65441.2025.11433840","title":"Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement","display_name":"Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148513141","doi":"https://doi.org/10.1109/asru65441.2025.11433840"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11433840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","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/A5059048857","display_name":"Heitor R. Guimar\u00e3es","orcid":"https://orcid.org/0000-0001-9929-9871"},"institutions":[{"id":"https://openalex.org/I39481719","display_name":"Institut National de la Recherche Scientifique","ror":"https://ror.org/04td37d32","country_code":"CA","type":"education","lineage":["https://openalex.org/I39481719","https://openalex.org/I49663120"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Heitor R. Guimar\u00e3es","raw_affiliation_strings":["INRS - EMT,Montreal,CA"],"affiliations":[{"raw_affiliation_string":"INRS - EMT,Montreal,CA","institution_ids":["https://openalex.org/I39481719"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075227645","display_name":"Ke Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Tan","raw_affiliation_strings":["Meta Reality Labs,Redmond,US"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Redmond,US","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011286001","display_name":"Juan Azcarreta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Azcarreta","raw_affiliation_strings":["Meta Reality Labs,Cambridge,UK"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Cambridge,UK","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132819357","display_name":"Jesus M. Alvarez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jesus M. Alvarez","raw_affiliation_strings":["Meta Reality Labs,ES"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,ES","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043514543","display_name":"Prabhav Agrawal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112286","display_name":"The Metropolitan Opera (United States)","ror":"https://ror.org/022q3vw94","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112286"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prabhav Agrawal","raw_affiliation_strings":["Meta AI,New York,US"],"affiliations":[{"raw_affiliation_string":"Meta AI,New York,US","institution_ids":["https://openalex.org/I4210112286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132823702","display_name":"Ashutosh Pandey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Meta Reality Labs,Redmond,US"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Redmond,US","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130819187","display_name":"Buye Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs,Redmond,US"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,Redmond,US","institution_ids":["https://openalex.org/I4210128585"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5059048857"],"corresponding_institution_ids":["https://openalex.org/I39481719"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75313592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9830999970436096,"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":0.9830999970436096,"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":0.003800000064074993,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.002300000051036477,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.678600013256073},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5615000128746033},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5302000045776367},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46959999203681946},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45649999380111694},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4203000068664551},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.4165000021457672},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.37400001287460327},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.364300012588501},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3456999957561493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922000288963318},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.678600013256073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5615000128746033},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909000098705292},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.364300012588501},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3456999957561493},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31790000200271606},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11433840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11433840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.44317829608917236,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2133665775","https://openalex.org/W2141998673","https://openalex.org/W2897371647","https://openalex.org/W3015338123","https://openalex.org/W3096429957","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3152148971","https://openalex.org/W3161480375","https://openalex.org/W3163652268","https://openalex.org/W4206319965","https://openalex.org/W4224925070","https://openalex.org/W4225273076","https://openalex.org/W4245919820","https://openalex.org/W4247068223","https://openalex.org/W4296069327","https://openalex.org/W4367281387","https://openalex.org/W4385822774","https://openalex.org/W4390604176","https://openalex.org/W4392902611","https://openalex.org/W4392903047","https://openalex.org/W4392903427","https://openalex.org/W4402112230","https://openalex.org/W4402112296","https://openalex.org/W4402115964","https://openalex.org/W4404609118","https://openalex.org/W4408352921","https://openalex.org/W4408353433","https://openalex.org/W4408353719","https://openalex.org/W7133219565"],"related_works":[],"abstract_inverted_index":{"Deploying":[0],"speech":[1,59],"enhancement":[2],"(SE)":[3],"systems":[4],"in":[5],"wearable":[6],"devices,":[7],"such":[8],"as":[9],"smart":[10],"glasses,":[11],"is":[12,97],"challenging":[13],"due":[14],"to":[15,90],"the":[16,21,87,92,109],"limited":[17],"computational":[18,32],"resources":[19],"on":[20,37],"device.":[22],"Although":[23],"deep":[24],"learning":[25],"methods":[26],"have":[27],"achieved":[28],"high-quality":[29,58],"results,":[30],"their":[31,35],"cost":[33],"limits":[34],"feasibility":[36],"embedded":[38],"platforms.":[39],"This":[40],"work":[41],"presents":[42],"an":[43],"efficient":[44],"end-to-end":[45,99],"SE":[46],"framework":[47],"that":[48,117],"leverages":[49],"a":[50,62],"Differentiable":[51],"Digital":[52],"Signal":[53],"Processing":[54],"(DDSP)":[55],"vocoder":[56,89],"for":[57,140],"synthesis.":[60],"First,":[61],"compact":[63],"neural":[64],"network":[65],"predicts":[66],"enhanced":[67,93],"acoustic":[68],"features":[69,83],"from":[70],"noisy":[71],"speech:":[72],"spectral":[73],"envelope,":[74],"fundamental":[75],"frequency":[76],"(F<inf":[77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>),":[79],"and":[80,102,111,122,127],"periodicity.":[81],"These":[82],"are":[84],"fed":[85],"into":[86],"DDSP":[88],"synthesize":[91],"waveform.":[94],"The":[95],"system":[96],"trained":[98],"with":[100],"STFT":[101],"adversarial":[103],"losses,":[104],"enabling":[105],"direct":[106],"optimization":[107],"at":[108],"feature":[110],"waveform":[112],"levels.":[113],"Experimental":[114],"results":[115],"show":[116],"our":[118],"method":[119],"improves":[120],"intelligibility":[121],"quality":[123],"by":[124],"4%":[125],"(STOI)":[126],"19%":[128],"(DNSMOS)":[129],"over":[130],"strong":[131],"baselines":[132],"without":[133],"significantly":[134],"increasing":[135],"computation,":[136],"making":[137],"it":[138],"well-suited":[139],"real-time":[141],"applications.":[142]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}