{"id":"https://openalex.org/W7160099192","doi":"https://doi.org/10.48550/arxiv.2605.00329","title":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","display_name":"Fast Text-to-Audio Generation with One-Step Sampling via Energy-Scoring and Auxiliary Contextual Representation Distillation","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160099192","doi":"https://doi.org/10.48550/arxiv.2605.00329"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00329","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.00329","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135105880","display_name":"Kuan-Po Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Kuan-Po","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074851450","display_name":"Bo-Ru Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Bo-Ru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135116345","display_name":"Byeonggeun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Byeonggeun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049483143","display_name":"Mihee Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Mihee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088599790","display_name":"Zalan Fabian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian, Zalan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059545916","display_name":"Renard Korzeniowski","orcid":"https://orcid.org/0009-0004-8759-803X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korzeniowski, Renard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101986528","display_name":"Qingming Tang","orcid":"https://orcid.org/0000-0002-2670-4917"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Qingming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135234418","display_name":"Greg Ver Steeg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steeg, Greg Ver","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135125230","display_name":"Hung-yi Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Hung-yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020775828","display_name":"Chieh-Chi Kao","orcid":"https://orcid.org/0000-0002-1161-3959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kao, Chieh-Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135276631","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-1989-2718"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.3181000053882599,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.3181000053882599,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.12939999997615814,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11029999703168869,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/autoregressive-model","display_name":"Autoregressive model","score":0.6360999941825867},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.6269999742507935},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.583899974822998},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5784000158309937},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5234000086784363},{"id":"https://openalex.org/keywords/importance-sampling","display_name":"Importance sampling","score":0.4571000039577484},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41929998993873596},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.413100004196167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6992999911308289},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.6269999742507935},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5784000158309937},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5234000086784363},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49570000171661377},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38519999384880066},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C68710425","wikidata":"https://www.wikidata.org/wiki/Q5275442","display_name":"Diffusion process","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2867000102996826},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C114996537","wikidata":"https://www.wikidata.org/wiki/Q4854529","display_name":"Colors of noise","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00329","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.00329","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00329","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7952463030815125}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"(AR)":[1],"models":[2],"with":[3,39,116,136,148],"diffusion":[4,62,80,114,124],"heads":[5],"have":[6],"recently":[7],"achieved":[8],"strong":[9,76],"text-to-audio":[10,72,158],"performance,":[11],"yet":[12],"their":[13],"iterative":[14],"decoding":[15],"and":[16,98,103],"multi-step":[17,117],"sampling":[18,31,63],"process":[19],"introduce":[20],"high-latency":[21],"issues.":[22],"To":[23],"address":[24],"this":[25],"bottleneck,":[26],"we":[27],"propose":[28],"a":[29,59,68],"one-step":[30,91],"framework":[32],"that":[33,144],"combines":[34],"an":[35,152],"energy-distance":[36,146],"training":[37,147],"objective":[38,102],"representation-level":[40,149],"distillation.":[41],"An":[42],"energy-scoring":[43],"head":[44],"maps":[45],"Gaussian":[46],"noise":[47],"directly":[48],"to":[49,112,120,131],"audio":[50,139],"latents":[51],"in":[52],"one":[53],"step,":[54],"eliminating":[55],"the":[56,75,83,109,121],"need":[57],"for":[58,155],"costly":[60],"recursive":[61],"process,":[64],"while":[65,106],"distillation":[66,150],"from":[67],"masked":[69],"autoregressive":[70],"(MAR)":[71],"model":[73],"preserves":[74],"conditioning":[77],"learned":[78],"during":[79],"training.":[81],"On":[82],"AudioCaps":[84],"benchmark,":[85],"our":[86,127],"method":[87],"consistently":[88],"outperforms":[89],"prior":[90],"baselines":[92],"such":[93],"as":[94],"ConsistencyTTA,":[95],"SoundCTM,":[96],"AudioLCM":[97],"AudioTurbo,":[99],"on":[100],"both":[101],"subjective":[104],"metrics,":[105],"substantially":[107],"narrowing":[108],"quality":[110],"gap":[111],"AR":[113,123],"systems":[115],"sampling.":[118],"Compared":[119],"state-of-the-art":[122],"system,":[125],"IMPACT,":[126],"approach":[128],"achieves":[129],"up":[130],"$8.5$x":[132],"faster":[133],"batch":[134],"inference":[135],"highly":[137],"competitive":[138],"quality.":[140],"These":[141],"results":[142],"demonstrate":[143],"combining":[145],"provides":[151],"effective":[153],"recipe":[154],"fast,":[156],"high-quality":[157],"synthesis.":[159]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-05T00:00:00"}