{"id":"https://openalex.org/W4408354211","doi":"https://doi.org/10.1109/icassp49660.2025.10890704","title":"Audio Texture Manipulation by Exemplar-Based Analogy","display_name":"Audio Texture Manipulation by Exemplar-Based Analogy","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354211","doi":"https://doi.org/10.1109/icassp49660.2025.10890704"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890704","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":"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/A5107883428","display_name":"K. y. Cheng","orcid":"https://orcid.org/0000-0003-0825-7903"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kan Jen Cheng","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054695986","display_name":"Tingle Li","orcid":"https://orcid.org/0000-0003-1654-8030"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tingle Li","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092897580","display_name":"Gopala Anumanchipalli","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala Anumanchipalli","raw_affiliation_strings":["University of California,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107883428"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0427106,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9437000155448914,"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":0.9437000155448914,"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":0.9294999837875366,"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/analogy","display_name":"Analogy","score":0.7963448762893677},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7394501566886902},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.6253896355628967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5689912438392639},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.47634485363960266},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.36179208755493164},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3447919487953186},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09534820914268494}],"concepts":[{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.7963448762893677},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394501566886902},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.6253896355628967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5689912438392639},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47634485363960266},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36179208755493164},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3447919487953186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09534820914268494},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890704","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":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1965555277","https://openalex.org/W2062663442","https://openalex.org/W2067295501","https://openalex.org/W2103869314","https://openalex.org/W2194775991","https://openalex.org/W2292976057","https://openalex.org/W2593116425","https://openalex.org/W2603567530","https://openalex.org/W2737697117","https://openalex.org/W2945761034","https://openalex.org/W4205689591","https://openalex.org/W4221046558","https://openalex.org/W4312933868","https://openalex.org/W4372266552","https://openalex.org/W4385807442","https://openalex.org/W4386071828","https://openalex.org/W4402660160","https://openalex.org/W4403760386","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757220786","https://openalex.org/W6757817989","https://openalex.org/W6779823529","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6802968314","https://openalex.org/W6809646742","https://openalex.org/W6840815571","https://openalex.org/W6843258702","https://openalex.org/W6845413636","https://openalex.org/W6849109464","https://openalex.org/W6851290578","https://openalex.org/W6857005093"],"related_works":["https://openalex.org/W2392206215","https://openalex.org/W2365201483","https://openalex.org/W2355561779","https://openalex.org/W2352407775","https://openalex.org/W108701362","https://openalex.org/W2186567693","https://openalex.org/W2469799552","https://openalex.org/W2768582344","https://openalex.org/W28964973","https://openalex.org/W2615704157"],"abstract_inverted_index":{"Audio":[0],"texture":[1,34],"manipulation":[2,75],"involves":[3],"modifying":[4],"the":[5,52,58,66,74],"perceptual":[6,104],"characteristics":[7],"of":[8,37,76],"a":[9,81,90,95],"sound":[10,54,77],"to":[11,64,69,114],"achieve":[12],"specific":[13],"transformations,":[14],"such":[15],"as":[16],"adding,":[17],"removing,":[18],"or":[19],"replacing":[20],"auditory":[21],"elements.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"propose":[27],"an":[28],"exemplar-based":[29],"analogy":[30],"model":[31,62,93,108],"for":[32,73],"audio":[33],"manipulation.":[35],"Instead":[36],"conditioning":[38],"on":[39],"text-based":[40],"instructions,":[41],"our":[42,107],"method":[43],"uses":[44],"paired":[45],"speech":[46],"examples,":[47],"where":[48],"one":[49],"clip":[50],"represents":[51],"original":[53],"and":[55,88,103,112,117],"another":[56],"illustrates":[57],"desired":[59],"transformation.":[60],"The":[61],"learns":[63],"apply":[65],"same":[67],"transformation":[68],"new":[70],"input,":[71],"allowing":[72],"textures.":[78],"We":[79,98],"construct":[80],"quadruplet":[82],"dataset":[83],"representing":[84],"various":[85],"editing":[86],"tasks,":[87],"train":[89],"latent":[91],"diffusion":[92],"in":[94],"self-supervised":[96],"manner.":[97],"show":[99],"through":[100],"quantitative":[101],"evaluations":[102],"studies":[105],"that":[106],"outperforms":[109],"text-conditioned":[110],"baselines":[111],"generalizes":[113],"real-world,":[115],"out-of-distribution,":[116],"non-speech":[118],"scenarios.":[119]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}