{"id":"https://openalex.org/W2938577267","doi":"https://doi.org/10.1109/icassp.2019.8682598","title":"Audio Texture Synthesis with Random Neural Networks: Improving Diversity and Quality","display_name":"Audio Texture Synthesis with Random Neural Networks: Improving Diversity and Quality","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938577267","doi":"https://doi.org/10.1109/icassp.2019.8682598","mag":"2938577267"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5020381382","display_name":"Joseph M. Antognini","orcid":"https://orcid.org/0000-0002-5976-5396"},"institutions":[{"id":"https://openalex.org/I4210127493","display_name":"Xperi (United States)","ror":"https://ror.org/03jn2ja08","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph M. Antognini","raw_affiliation_strings":["Whisper AI, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Whisper AI, Inc","institution_ids":["https://openalex.org/I4210127493"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052225069","display_name":"Matt Hoffman","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":"Matt Hoffman","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"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":"Ron J. Weiss","raw_affiliation_strings":["Google, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"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":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3587","last_page":"3591"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9962999820709229,"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":0.9868000149726868,"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":0.7894236445426941},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5639153122901917},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.5455855131149292},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.5372955799102783},{"id":"https://openalex.org/keywords/gramian-matrix","display_name":"Gramian matrix","score":0.5126416087150574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.510924756526947},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.47682470083236694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4762323498725891},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4762064218521118},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.4596185088157654},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43439826369285583},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4317496120929718},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4149106740951538},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40962228178977966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3671455383300781},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.265595018863678},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.1989072859287262},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18704989552497864},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.12895247340202332},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12353125214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894236445426941},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5639153122901917},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.5455855131149292},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.5372955799102783},{"id":"https://openalex.org/C77246614","wikidata":"https://www.wikidata.org/wiki/Q1409400","display_name":"Gramian matrix","level":3,"score":0.5126416087150574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.510924756526947},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.47682470083236694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4762323498725891},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4762064218521118},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.4596185088157654},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43439826369285583},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4317496120929718},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4149106740951538},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40962228178977966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3671455383300781},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.265595018863678},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.1989072859287262},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18704989552497864},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.12895247340202332},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12353125214576721},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":22,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W2005126631","https://openalex.org/W2062663442","https://openalex.org/W2097117768","https://openalex.org/W2120847449","https://openalex.org/W2125027853","https://openalex.org/W2127006916","https://openalex.org/W2415655786","https://openalex.org/W2429018336","https://openalex.org/W2593116425","https://openalex.org/W2604712616","https://openalex.org/W2737664244","https://openalex.org/W2962899986","https://openalex.org/W2963373786","https://openalex.org/W2964193438","https://openalex.org/W4241568739","https://openalex.org/W6631943919","https://openalex.org/W6683590716","https://openalex.org/W6716561791","https://openalex.org/W6717740044","https://openalex.org/W6718379498","https://openalex.org/W6736034361"],"related_works":["https://openalex.org/W4390355884","https://openalex.org/W747394405","https://openalex.org/W1987236514","https://openalex.org/W174653542","https://openalex.org/W2381153750","https://openalex.org/W4302344890","https://openalex.org/W2041235277","https://openalex.org/W2088220880","https://openalex.org/W2022021973","https://openalex.org/W4320858924"],"abstract_inverted_index":{"Texture":[0],"synthesis":[1],"techniques":[2,29],"based":[3],"on":[4,93],"matching":[5],"the":[6,20,31,61,77,87,94,97,106,112,123,128,149,152],"Gram":[7],"matrix":[8],"of":[9,89,96,127,139,151],"feature":[10],"activations":[11],"in":[12,19],"neural":[13],"networks":[14],"have":[15],"achieved":[16],"spectacular":[17],"success":[18],"image":[21],"domain.":[22,33],"In":[23],"this":[24,46,132],"paper":[25],"we":[26,110,135],"extend":[27],"these":[28,145],"to":[30,60,80,105,141],"audio":[32,39,49,99,103,130],"We":[34,54,84,115],"demonstrate":[35],"that":[36,45,68,75,117],"synthesizing":[37],"diverse":[38],"textures":[40],"is":[41,47,51,119],"challenging,":[42],"and":[43,71,125],"argue":[44],"because":[48],"data":[50],"relatively":[52],"low-dimensional.":[53],"therefore":[55],"introduce":[56],"two":[57],"new":[58],"terms":[59],"original":[62],"Grammian":[63],"loss:":[64],"an":[65,102],"autocorrelation":[66],"term":[67,74,111],"preserves":[69],"rhythm,":[70],"a":[72,120,137],"diversity":[73,124],"encourages":[76],"optimization":[78],"procedure":[79],"synthesize":[81],"unique":[82],"textures.":[83],"quantitatively":[85],"study":[86,143],"impact":[88,148],"our":[90],"design":[91,146],"choices":[92,147],"quality":[95,126,150],"synthesized":[98,129,153],"by":[100],"introducing":[101],"analogue":[104],"Inception":[107],"loss":[108],"which":[109],"VGGish":[113],"loss.":[114],"show":[116],"there":[118],"trade-off":[121],"between":[122],"using":[131],"technique.":[133],"Finally":[134],"perform":[136],"number":[138],"experiments":[140],"qualitatively":[142],"how":[144],"audio.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}