{"id":"https://openalex.org/W4408354662","doi":"https://doi.org/10.1109/icassp49660.2025.10890760","title":"Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration With Improved Intelligibility","display_name":"Joint Semantic Knowledge Distillation and Masked Acoustic Modeling for Full-band Speech Restoration With Improved Intelligibility","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354662","doi":"https://doi.org/10.1109/icassp49660.2025.10890760"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890760","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":["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/A5100455531","display_name":"Xiaoyu Liu","orcid":"https://orcid.org/0009-0005-6402-3855"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Xiaoyu Liu","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342504","display_name":"Xu Li","orcid":"https://orcid.org/0009-0004-7507-4669"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044197796","display_name":"Joan Serr\u00e0","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joan Serr\u00e0","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101557983","display_name":"Santiago Pascual","orcid":"https://orcid.org/0000-0002-8365-7387"},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Santiago Pascual","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100455531"],"corresponding_institution_ids":["https://openalex.org/I116121188"],"apc_list":null,"apc_paid":null,"fwci":8.5798,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96862812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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":0.9922999739646912,"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":0.9758999943733215,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9129999876022339,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7252529859542847},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7236635684967041},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6206018328666687},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5110026597976685},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1463896632194519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252529859542847},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7236635684967041},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6206018328666687},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5110026597976685},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1463896632194519},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890760","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2603567530","https://openalex.org/W2963242190","https://openalex.org/W3015191643","https://openalex.org/W3097906045","https://openalex.org/W3097945073","https://openalex.org/W3160077247","https://openalex.org/W3161480375","https://openalex.org/W3163113319","https://openalex.org/W3197260772","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4224917453","https://openalex.org/W4225905067","https://openalex.org/W4226185896","https://openalex.org/W4252812408","https://openalex.org/W4281820413","https://openalex.org/W4313021454","https://openalex.org/W4313120002","https://openalex.org/W4372340947","https://openalex.org/W4376877074","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W4385822723","https://openalex.org/W4386764084","https://openalex.org/W4386764866","https://openalex.org/W4390075359","https://openalex.org/W4392909571","https://openalex.org/W4396877837","https://openalex.org/W4400111385","https://openalex.org/W4402111399","https://openalex.org/W4402112296","https://openalex.org/W6802017037","https://openalex.org/W6840815571","https://openalex.org/W6849105126","https://openalex.org/W6853515095","https://openalex.org/W6855885476","https://openalex.org/W6857125635","https://openalex.org/W6936113694"],"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/W2127461790","https://openalex.org/W2069324367"],"abstract_inverted_index":{"Speech":[0],"restoration":[1],"aims":[2],"at":[3],"restoring":[4],"full-band":[5],"speech":[6,53],"with":[7,58,102],"high":[8,36],"quality":[9,37],"and":[10,108],"intelligibility,":[11],"considering":[12],"a":[13,20,68,74,121],"diverse":[14],"set":[15],"of":[16,31,56,60,63,95,146],"distortions.":[17],"MaskSR":[18,34,57,105],"is":[19,78],"recently":[21],"proposed":[22,112],"generative":[23],"model":[24,77,106],"for":[25,124],"this":[26],"task.":[27],"As":[28],"other":[29,134],"models":[30],"its":[32],"kind,":[33],"attains":[35],"but,":[38],"as":[39],"we":[40],"show,":[41],"intelligibility":[42],"can":[43],"be":[44],"substantially":[45],"improved.":[46],"We":[47,99],"do":[48],"so":[49],"by":[50],"boosting":[51],"the":[52,64,81,96,103,111,117,144],"encoder":[54],"component":[55],"predictions":[59],"semantic":[61,83,148],"representations":[62],"target":[65,97],"speech,":[66],"using":[67],"pre-trained":[69],"self-supervised":[70],"teacher":[71],"model.":[72],"Then,":[73],"masked":[75],"language":[76],"conditioned":[79],"on":[80],"learned":[82],"features":[84],"to":[85],"predict":[86],"acoustic":[87],"tokens":[88],"that":[89],"encode":[90],"low":[91],"level":[92],"spectral":[93],"details":[94],"speech.":[98],"show":[100],"that,":[101],"same":[104],"capacity":[107],"inference":[109],"time,":[110],"model,":[113],"MaskSR2,":[114],"significantly":[115],"reduces":[116],"word":[118,130],"error":[119,131],"rate,":[120],"typical":[122],"metric":[123],"intelligibility.":[125],"MaskSR2":[126],"also":[127],"achieves":[128],"competitive":[129],"rate":[132],"among":[133],"models,":[135],"while":[136],"providing":[137],"superior":[138],"quality.":[139],"An":[140],"ablation":[141],"study":[142],"shows":[143],"effectiveness":[145],"various":[147],"representations.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
