{"id":"https://openalex.org/W4392904425","doi":"https://doi.org/10.1109/icassp48485.2024.10448220","title":"Audio-Journey: Open Domain Latent Diffusion Based Text-To-Audio Generation","display_name":"Audio-Journey: Open Domain Latent Diffusion Based Text-To-Audio Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904425","doi":"https://doi.org/10.1109/icassp48485.2024.10448220"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5109692722","display_name":"Jackson Michaels","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jackson Michaels","raw_affiliation_strings":["Northwestern University,Chicago,IL","Northwestern University, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Chicago,IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, Chicago, IL","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004697852","display_name":"Juncheng B Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng B Li","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA","Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059554438","display_name":"Laura Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Yao","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA","Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100575170","display_name":"Lijun Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijun Yu","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA","Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059956805","display_name":"Zach Wood-Doughty","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zach Wood-Doughty","raw_affiliation_strings":["Northwestern University,Chicago,IL","Northwestern University, Chicago, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Chicago,IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, Chicago, IL","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,PA","Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2229,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76856219,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6960","last_page":"6964"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T11349","display_name":"Music Technology and Sound Studies","score":0.9925000071525574,"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/T10860","display_name":"Speech and Audio Processing","score":0.9884999990463257,"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":0.8342480659484863},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6360193490982056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5251283645629883},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5138568878173828},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4691321551799774},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46735408902168274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4344913065433502},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4316581189632416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3354484438896179},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1897260844707489},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10007080435752869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8342480659484863},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6360193490982056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5251283645629883},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5138568878173828},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4691321551799774},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46735408902168274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4344913065433502},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4316581189632416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3354484438896179},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1897260844707489},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10007080435752869},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":36,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2959300817","https://openalex.org/W2964303773","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3121370741","https://openalex.org/W3129651364","https://openalex.org/W3162926177","https://openalex.org/W4226148126","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4300980117","https://openalex.org/W4307323391","https://openalex.org/W4312933868","https://openalex.org/W4318348481","https://openalex.org/W4318718936","https://openalex.org/W4318752004","https://openalex.org/W4367359628","https://openalex.org/W4372260310","https://openalex.org/W4400033239","https://openalex.org/W6759579507","https://openalex.org/W6765775151","https://openalex.org/W6769627184","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6791353385","https://openalex.org/W6795288823","https://openalex.org/W6811424244","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849177959","https://openalex.org/W6849390846","https://openalex.org/W6853685229"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W2993670781"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress,":[2],"machine":[3],"learning":[4],"(ML)":[5],"models":[6,17],"for":[7,18,35,75],"open-domain":[8,28,166],"audio":[9,29,63,81,92,146,167],"generation":[10,147,152],"need":[11],"to":[12,15,57,72,89,96,130,150],"catch":[13],"up":[14],"generative":[16],"image,":[19],"text,":[20],"speech,":[21],"and":[22,84,93,158,172],"music.":[23],"The":[24,169],"lack":[25],"of":[26,107],"massive":[27],"datasets":[30],"is":[31,140],"the":[32,61,76,80,91,105,143],"main":[33],"reason":[34],"this":[36,41],"performance":[37],"gap;":[38],"we":[39,85,124],"overcome":[40],"challenge":[42],"through":[43],"a":[44,68,98,112,126],"novel":[45,141],"data":[46,82],"augmentation":[47],"approach.":[48],"We":[49,65,102],"leverage":[50],"state-of-the-art":[51],"(SOTA)":[52],"Large":[53],"Language":[54],"Models":[55],"(LLMs)":[56],"enrich":[58],"captions":[59,74,95],"in":[60,115,132,142],"weakly-labeled":[62],"dataset.":[64,101],"then":[66],"use":[67,87],"SOTA":[69,145],"video-captioning":[70],"model":[71,139],"generate":[73,131],"videos":[77],"from":[78],"which":[79],"originated,":[83],"again":[86],"LLMs":[88],"merge":[90],"video":[94],"form":[97],"rich,":[99],"large-scale":[100],"experimentally":[103],"evaluate":[104],"quality":[106],"our":[108,121,151],"audio-visual":[109],"captions,":[110],"showing":[111],"12.5%":[113],"gain":[114],"semantic":[116],"score":[117],"over":[118],"baselines.":[119],"Using":[120],"augmented":[122],"dataset,":[123],"train":[125],"Latent":[127],"Diffusion":[128],"Model":[129],"an":[133],"encodec":[134],"encoding":[135],"latent":[136],"space.":[137],"Our":[138],"current":[144],"landscape":[148],"due":[149],"space,":[153],"text":[154],"encoder,":[155],"noise":[156],"schedule,":[157],"attention":[159],"mechanism.":[160],"Together,":[161],"these":[162],"innovations":[163],"provide":[164],"competitive":[165],"generation.":[168],"samples,":[170],"models,":[171],"implementation":[173],"will":[174],"be":[175],"at":[176],"https://audiojourney.github.io.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}