{"id":"https://openalex.org/W4408355181","doi":"https://doi.org/10.1109/icassp49660.2025.10888073","title":"Audio Diffusion with Large Language Models","display_name":"Audio Diffusion with Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355181","doi":"https://doi.org/10.1109/icassp49660.2025.10888073"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888073","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/A5101673889","display_name":"Yinghui Huang","orcid":"https://orcid.org/0000-0003-0607-1507"},"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":"Yinghui Huang","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/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/A5015927589","display_name":"Kartik Audhkhasi","orcid":"https://orcid.org/0000-0002-2340-1144"},"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":"Kartik Audhkhasi","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/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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024773539","display_name":"Andrew Rosenberg","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":"Andrew Rosenberg","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/T11309","display_name":"Music and Audio Processing","score":0.989799976348877,"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/T11309","display_name":"Music and Audio Processing","score":0.989799976348877,"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":0.9835000038146973,"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":0.9537000060081482,"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":0.6923149824142456},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.608617901802063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923149824142456},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.608617901802063},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888073","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":49,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1901129140","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2973122799","https://openalex.org/W3016234571","https://openalex.org/W3198862519","https://openalex.org/W4225329198","https://openalex.org/W4285192675","https://openalex.org/W4297841228","https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4372269772","https://openalex.org/W4372346318","https://openalex.org/W4385822949","https://openalex.org/W4387195417","https://openalex.org/W4389524500","https://openalex.org/W4390872297","https://openalex.org/W4390873030","https://openalex.org/W4390873054","https://openalex.org/W4391021684","https://openalex.org/W4392903288","https://openalex.org/W4402306396","https://openalex.org/W4406461487","https://openalex.org/W6765469073","https://openalex.org/W6771467084","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6797359156","https://openalex.org/W6809646742","https://openalex.org/W6809884996","https://openalex.org/W6810334672","https://openalex.org/W6838639034","https://openalex.org/W6840815571","https://openalex.org/W6849744127","https://openalex.org/W6850218400","https://openalex.org/W6850392273","https://openalex.org/W6853998256","https://openalex.org/W6854652134","https://openalex.org/W6855414158","https://openalex.org/W6861618871","https://openalex.org/W6861626678","https://openalex.org/W6861859833","https://openalex.org/W6869907245","https://openalex.org/W6870337495","https://openalex.org/W6872492781","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/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"explore":[4],"an":[5],"alternate":[6],"approach":[7],"to":[8,33,37,52,61,71,100,122],"the":[9,47,56,63,72,95,110,115],"popular":[10],"method":[11],"of":[12,65,112],"using":[13],"large":[14],"language":[15],"models":[16],"(LLMs)":[17],"as":[18],"a":[19,39],"second":[20],"decoder":[21],"for":[22],"Automated":[23],"Speech":[24],"Recognition":[25],"(ASR)":[26],"and":[27,89,106,117],"speech":[28],"understanding":[29],"tasks.":[30],"We":[31,92],"propose":[32],"employ":[34],"diffusion":[35,57,96],"networks":[36],"generate":[38],"correction":[40],"signal":[41],"that":[42,94],"can":[43],"be":[44],"applied":[45],"on":[46,77,84,104],"original":[48],"input":[49,73],"audio":[50,74],"features":[51,75],"improve":[53,101,120],"performance.":[54],"Specifically,":[55],"network":[58],"is":[59,98],"trained":[60],"predict":[62],"gradient":[64],"any":[66],"ASR":[67,102],"objective":[68],"with":[69,109],"respect":[70],"conditioned":[76],"LLM":[78],"embeddings.":[79],"Our":[80],"experiments":[81],"are":[82],"conducted":[83],"public":[85],"corpora,":[86],"namely,":[87],"Librispeech":[88],"Common":[90],"Voice.":[91],"show":[93],"model":[97],"able":[99],"performance":[103],"noisy":[105],"accented":[107],"speech,":[108],"addition":[111],"knowledge":[113],"from":[114],"LLM,":[116],"also":[118],"helps":[119],"generalization":[121],"out-of-domain":[123],"test":[124],"sets.":[125]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}