{"id":"https://openalex.org/W4408353996","doi":"https://doi.org/10.1109/icassp49660.2025.10889043","title":"AudioCache: Accelerate Audio Generation With Training-Free Layer Caching","display_name":"AudioCache: Accelerate Audio Generation With Training-Free Layer Caching","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353996","doi":"https://doi.org/10.1109/icassp49660.2025.10889043"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889043","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/A5066253638","display_name":"Qingyang Shi","orcid":"https://orcid.org/0000-0003-4299-5889"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Shi","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113983572","display_name":"Zhimin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Du","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108898629","display_name":"Jiasheng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiasheng Lu","raw_affiliation_strings":["Huawei Technologies Co., Ltd.,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd.,Shenzhen,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499914","display_name":"Yingshan Liang","orcid":"https://orcid.org/0000-0003-2264-5566"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingshan Liang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100390694","display_name":"Xinyu Zhang","orcid":"https://orcid.org/0000-0002-4069-5703"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101440891","display_name":"Yiran Wang","orcid":"https://orcid.org/0000-0002-9062-4751"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Wang","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115588630","display_name":"Jing Peng","orcid":"https://orcid.org/0009-0002-0858-1527"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Peng","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102309342","display_name":"Kehong Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehong Yuan","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.9954000115394592,"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":0.9954000115394592,"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":0.9904999732971191,"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/T12031","display_name":"Speech and dialogue systems","score":0.9768000245094299,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8102960586547852},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.684930145740509},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.6614461541175842},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.43744564056396484},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.40360957384109497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102960586547852},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.684930145740509},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.6614461541175842},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.43744564056396484},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.40360957384109497},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889043","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":38,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2945761034","https://openalex.org/W2972478942","https://openalex.org/W3205475937","https://openalex.org/W4206662443","https://openalex.org/W4372260310","https://openalex.org/W4390872297","https://openalex.org/W4401024632","https://openalex.org/W4402111476","https://openalex.org/W4402778510","https://openalex.org/W4402816687","https://openalex.org/W4402917085","https://openalex.org/W4408345930","https://openalex.org/W4411528087","https://openalex.org/W6739901393","https://openalex.org/W6769627184","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6797854001","https://openalex.org/W6838327568","https://openalex.org/W6849416043","https://openalex.org/W6850464469","https://openalex.org/W6852874946","https://openalex.org/W6852971826","https://openalex.org/W6853011858","https://openalex.org/W6853096648","https://openalex.org/W6853622345","https://openalex.org/W6858779713","https://openalex.org/W6859898909","https://openalex.org/W6861353174","https://openalex.org/W6864565647","https://openalex.org/W6864798992","https://openalex.org/W6866562102","https://openalex.org/W6868481800","https://openalex.org/W6869001559","https://openalex.org/W6869055344","https://openalex.org/W6869178242","https://openalex.org/W6870301521"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Diffusion":[0,28],"models":[1,68,123,144],"have":[2],"become":[3],"the":[4,27,34,57,71,87,95],"primary":[5],"choice":[6],"in":[7,36],"audio":[8,20,37,66],"generation.":[9,38],"However,":[10],"their":[11],"slow":[12],"generation":[13,21,67],"speed":[14],"necessitates":[15],"acceleration":[16,106],"techniques.":[17],"While":[18],"current":[19],"methods":[22],"primarily":[23],"target":[24],"U-Net-based":[25],"models,":[26],"Transformer":[29],"(DiT)":[30],"is":[31,119],"emerging":[32],"as":[33],"trend":[35],"As":[39],"DiT":[40,77],"costs":[41],"a":[42,51,82,98,104,137],"large":[43],"amount":[44],"of":[45,76,89,97],"computational":[46],"resources,":[47],"we":[48],"propose":[49],"AudioCache:":[50],"training-free":[52,140],"caching":[53,100],"strategy":[54],"that,":[55],"for":[56,142],"first":[58],"time":[59],"to":[60,85,94,121],"our":[61,117],"best":[62],"knowledge,":[63],"accelerates":[64],"DiT-based":[65],"by":[69],"reusing":[70],"attention":[72,147],"and":[73,110,124,131,139],"feedforward":[74],"layers":[75],"during":[78],"sampling.":[79],"We":[80,102],"define":[81],"reasonable":[83],"statistic":[84],"characterize":[86],"degree":[88],"internal":[90],"structure":[91],"variation,":[92],"leading":[93],"proposal":[96],"self-adaptive":[99],"strategy.":[101],"achieve":[103],"2.35x":[105],"with":[107],"both":[108],"objective":[109],"subjective":[111],"metrics":[112],"remaining":[113],"practically":[114],"consistent.":[115],"Furthermore,":[116],"method":[118,135],"extendable":[120],"different":[122],"input":[125],"modalities.":[126],"Based":[127],"on":[128,146],"appropriate":[129],"indicators":[130],"corresponding":[132],"rules,":[133],"this":[134],"provides":[136],"plug-and-play":[138],"solution":[141],"diffusion":[143],"built":[145],"architectures.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}