{"id":"https://openalex.org/W4408354359","doi":"https://doi.org/10.1109/icassp49660.2025.10888357","title":"Speech Re-Painting for Robust ASR","display_name":"Speech Re-Painting for Robust ASR","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354359","doi":"https://doi.org/10.1109/icassp49660.2025.10888357"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888357","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":"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/A5037751863","display_name":"Kyle Kastner","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Kastner","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025935520","display_name":"Gary Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary Wang","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063926383","display_name":"Isaac Elias","orcid":"https://orcid.org/0000-0001-9035-5419"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Elias","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048766619","display_name":"Pedro Moreno Mengibar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Moreno Mengibar","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110711540","display_name":"Fran\u00e7oise Beaufays","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7oise Beaufays","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102902866","display_name":"Andrew Rosenberg","orcid":"https://orcid.org/0000-0003-1780-4390"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Rosenberg","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["Google LLC,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9941999912261963,"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":0.9941999912261963,"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":0.9872000217437744,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9557999968528748,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6823269724845886},{"id":"https://openalex.org/keywords/painting","display_name":"Painting","score":0.6671881079673767},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5772809982299805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32894086837768555},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.17576563358306885},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.12911152839660645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823269724845886},{"id":"https://openalex.org/C205783811","wikidata":"https://www.wikidata.org/wiki/Q11629","display_name":"Painting","level":2,"score":0.6671881079673767},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5772809982299805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32894086837768555},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.17576563358306885},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.12911152839660645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888357","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":40,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1494198834","https://openalex.org/W2605102758","https://openalex.org/W2915977493","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W3008480565","https://openalex.org/W3015280134","https://openalex.org/W3097777922","https://openalex.org/W3161296985","https://openalex.org/W3197294703","https://openalex.org/W3198836239","https://openalex.org/W3208049241","https://openalex.org/W3212380917","https://openalex.org/W4225272718","https://openalex.org/W4226120743","https://openalex.org/W4252812408","https://openalex.org/W4296068407","https://openalex.org/W4372260611","https://openalex.org/W4372267196","https://openalex.org/W4372269772","https://openalex.org/W4375869005","https://openalex.org/W4386764866","https://openalex.org/W4390041933","https://openalex.org/W4391020683","https://openalex.org/W4391021675","https://openalex.org/W4392903365","https://openalex.org/W4392904149","https://openalex.org/W4392931212","https://openalex.org/W6640963894","https://openalex.org/W6772349387","https://openalex.org/W6802119844","https://openalex.org/W6845576796","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6850218400","https://openalex.org/W6852421699","https://openalex.org/W6853998256","https://openalex.org/W6861859833","https://openalex.org/W6868695479"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2580687016","https://openalex.org/W2886265999","https://openalex.org/W2383951830","https://openalex.org/W1591565242","https://openalex.org/W2369092230","https://openalex.org/W2357187602","https://openalex.org/W2940819518"],"abstract_inverted_index":{"Synthetic":[0],"speech":[1,10,24,34,74,92],"is":[2,16,35],"a":[3,17,76,99,132],"useful":[4],"source":[5],"for":[6,67,78],"augmentation":[7,47],"of":[8,32,40,55,62,134],"automatic":[9],"recognition":[11],"(ASR)":[12],"systems,":[13],"but":[14],"there":[15],"\"sim-to-real\"":[18],"gap":[19],"between":[20],"synthetic":[21,45],"and":[22,93,116,123],"real":[23,33],"that":[25,126],"can":[26,48],"limit":[27],"generalization.":[28],"The":[29],"natural":[30,56],"variability":[31,54],"essential":[36],"to":[37,51,86],"the":[38,53,96,114],"training":[39,84],"robust":[41],"ASR":[42,108],"systems.":[43],"While":[44],"data":[46],"be":[49],"used":[50],"approximate":[52],"speech,":[57],"however,":[58],"not":[59],"all":[60],"aspects":[61],"variation":[63],"are":[64,127],"equally":[65],"relevant":[66],"augmentation.":[68],"In":[69],"this":[70,104],"work,":[71],"we":[72],"introduce":[73],"re-painting,":[75,130],"method":[77],"in-context":[79],"augmented":[80],"synthesis,":[81],"using":[82,106,113],"target":[83],"datasets":[85],"generate":[87],"new":[88],"utterances":[89],"guided":[90],"by":[91,129],"text":[94],"on":[95],"fly":[97],"in":[98,139],"zero-shot":[100],"manner.":[101],"We":[102],"evaluate":[103],"technique":[105],"downstream":[107],"word":[109],"error":[110],"rate":[111],"(WER)":[112],"VCTK":[115],"LibriSpeech":[117],"datasets.":[118],"These":[119],"represent":[120],"unique":[121],"speaker":[122],"lexical":[124],"challenges":[125],"addressed":[128],"realizing":[131],"reduction":[133],"WER":[135],"more":[136],"than":[137],"50%":[138],"particular":[140],"settings.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}