{"id":"https://openalex.org/W4408353418","doi":"https://doi.org/10.1109/icassp49660.2025.10888830","title":"Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration","display_name":"Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353418","doi":"https://doi.org/10.1109/icassp49660.2025.10888830"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888830","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/A5058318424","display_name":"Pin-Jui Ku","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pin-Jui Ku","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064142365","display_name":"Alexander H. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander H. Liu","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088645391","display_name":"Roman Korostik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roman Korostik","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071504898","display_name":"Sung-Feng Huang","orcid":"https://orcid.org/0000-0002-9720-811X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sung-Feng Huang","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071471469","display_name":"Szu\u2010Wei Fu","orcid":"https://orcid.org/0000-0002-3487-8212"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Szu-Wei Fu","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063860258","display_name":"Ante Juki\u0107","orcid":"https://orcid.org/0000-0003-2202-2203"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ante Juki\u0107","raw_affiliation_strings":["NVIDIA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058318424"],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":10.2848,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97659892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7049757838249207},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6683413982391357},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5477131009101868},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4759119153022766},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46282559633255005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4305141568183899},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36958324909210205},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.059277892112731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049757838249207},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6683413982391357},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5477131009101868},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4759119153022766},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46282559633255005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4305141568183899},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36958324909210205},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.059277892112731934},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/icassp49660.2025.10888830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888830","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2006129368","https://openalex.org/W2044893557","https://openalex.org/W2135823751","https://openalex.org/W2194775991","https://openalex.org/W2516001803","https://openalex.org/W2757519008","https://openalex.org/W2952218014","https://openalex.org/W2963341071","https://openalex.org/W2964058413","https://openalex.org/W2995181338","https://openalex.org/W3015636705","https://openalex.org/W3027008958","https://openalex.org/W3097653961","https://openalex.org/W3097756030","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3131332223","https://openalex.org/W3209984917","https://openalex.org/W4200634403","https://openalex.org/W4221144097","https://openalex.org/W4296070363","https://openalex.org/W4372260337","https://openalex.org/W4372268522","https://openalex.org/W4372341094","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4382603054","https://openalex.org/W4384080510","https://openalex.org/W4385807442","https://openalex.org/W4385822478","https://openalex.org/W4390306858","https://openalex.org/W4390872297","https://openalex.org/W4392903066","https://openalex.org/W4399345616","https://openalex.org/W4406461266","https://openalex.org/W6744762798","https://openalex.org/W6752307458","https://openalex.org/W6777776875","https://openalex.org/W6783867762","https://openalex.org/W6800569930","https://openalex.org/W6840815571","https://openalex.org/W6846539466","https://openalex.org/W6853515095","https://openalex.org/W6853888607","https://openalex.org/W6857325431","https://openalex.org/W6859583170"],"related_works":["https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2380075625","https://openalex.org/W2358060160","https://openalex.org/W2035483685","https://openalex.org/W1969764885","https://openalex.org/W596947562","https://openalex.org/W2793937822","https://openalex.org/W2790817834","https://openalex.org/W2777605427"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,35],"generative":[4],"pretraining":[5],"foundation":[6],"model":[7,23,38,86,102],"for":[8,30],"high-quality":[9],"speech":[10,65,69],"restoration":[11,66],"tasks.":[12],"By":[13],"directly":[14],"operating":[15],"on":[16,27,63],"complex-valued":[17],"short-time":[18],"Fourier":[19],"transform":[20],"coefficients,":[21],"our":[22,37,84,101],"does":[24],"not":[25],"rely":[26],"any":[28,50],"vocoders":[29],"time-domain":[31],"signal":[32],"reconstruction.":[33],"As":[34],"result,":[36],"simplifies":[39],"the":[40,45,96,116,123],"synthesis":[41],"process":[42],"and":[43,76,115],"removes":[44],"quality":[46],"upper-bound":[47],"introduced":[48],"by":[49],"mel-spectrogram":[51],"vocoder":[52],"compared":[53],"to":[54],"prior":[55],"work":[56],"SpeechFlow.":[57],"The":[58,113],"proposed":[59],"method":[60],"is":[61],"evaluated":[62],"multiple":[64],"tasks,":[67],"including":[68,106],"denoising,":[70],"bandwidth":[71],"extension,":[72],"codec":[73],"artifact":[74],"removal,":[75],"target":[77,97],"speaker":[78,98],"extraction.":[79],"In":[80],"all":[81],"scenarios,":[82],"finetuning":[83],"pretrained":[85,117],"results":[87],"in":[88,95,122],"superior":[89],"performance":[90],"over":[91],"strong":[92],"baselines.":[93],"Notably,":[94],"extraction":[99],"task,":[100],"outperforms":[103],"existing":[104],"systems,":[105],"those":[107],"leveraging":[108],"SSL-pretrained":[109],"encoders":[110],"like":[111],"WavLM.":[112],"code":[114],"checkpoints":[118],"are":[119],"publicly":[120],"available":[121],"NVIDIA":[124],"NeMo":[125],"framework.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}