{"id":"https://openalex.org/W4408352691","doi":"https://doi.org/10.1109/icassp49660.2025.10890049","title":"Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding","display_name":"Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352691","doi":"https://doi.org/10.1109/icassp49660.2025.10890049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890049","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/A5041479451","display_name":"Marco Pasini","orcid":"https://orcid.org/0000-0002-1430-7535"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Marco Pasini","raw_affiliation_strings":["Queen Mary University,London,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University,London,UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053442723","display_name":"Stefan Lattner","orcid":"https://orcid.org/0000-0002-3945-7580"},"institutions":[{"id":"https://openalex.org/I4210131385","display_name":"Sony (France)","ror":"https://ror.org/03cr99w51","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210131385","https://openalex.org/I4210143797"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Stefan Lattner","raw_affiliation_strings":["Sony Computer Science Laboratories,Paris,France"],"affiliations":[{"raw_affiliation_string":"Sony Computer Science Laboratories,Paris,France","institution_ids":["https://openalex.org/I4210131385"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy Fazekas","raw_affiliation_strings":["Queen Mary University,London,UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University,London,UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041479451"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.75465807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9907000064849854,"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":0.9889000058174133,"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/decoding-methods","display_name":"Decoding methods","score":0.7799817323684692},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7755200862884521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676589846611023},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6137067079544067},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5416072607040405},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.53061842918396},{"id":"https://openalex.org/keywords/dynamic-range-compression","display_name":"Dynamic range compression","score":0.5111778378486633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20483729243278503},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16204321384429932},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14536231756210327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1427001655101776},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11289238929748535}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7799817323684692},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7755200862884521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676589846611023},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6137067079544067},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5416072607040405},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.53061842918396},{"id":"https://openalex.org/C150178126","wikidata":"https://www.wikidata.org/wiki/Q18433212","display_name":"Dynamic range compression","level":2,"score":0.5111778378486633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20483729243278503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16204321384429932},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14536231756210327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1427001655101776},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11289238929748535},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890049","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":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317106","display_name":"Sony","ror":"https://ror.org/04wzv3n59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W1901129140","https://openalex.org/W2105910985","https://openalex.org/W2623662528","https://openalex.org/W2964058413","https://openalex.org/W2972478942","https://openalex.org/W3037038648","https://openalex.org/W3118215210","https://openalex.org/W3215615641","https://openalex.org/W4206662443","https://openalex.org/W4225905067","https://openalex.org/W4307323391","https://openalex.org/W4372260310","https://openalex.org/W4380434618","https://openalex.org/W4387968164","https://openalex.org/W4390872297","https://openalex.org/W4392908898","https://openalex.org/W4403363072","https://openalex.org/W4408345930","https://openalex.org/W6638787421","https://openalex.org/W6739901393","https://openalex.org/W6763945542","https://openalex.org/W6765775151","https://openalex.org/W6767164110","https://openalex.org/W6768465061","https://openalex.org/W6776218486","https://openalex.org/W6778946027","https://openalex.org/W6782757012","https://openalex.org/W6783713337","https://openalex.org/W6786375611","https://openalex.org/W6791537541","https://openalex.org/W6802552765","https://openalex.org/W6803637910","https://openalex.org/W6841472891","https://openalex.org/W6849105126","https://openalex.org/W6849517043","https://openalex.org/W6853096648","https://openalex.org/W6853393314","https://openalex.org/W6853515095","https://openalex.org/W6857468166","https://openalex.org/W6857470303","https://openalex.org/W6859841695","https://openalex.org/W6861353174","https://openalex.org/W6861862214","https://openalex.org/W6864565647","https://openalex.org/W6864798992","https://openalex.org/W6869704268","https://openalex.org/W6869989943","https://openalex.org/W6872080878"],"related_works":["https://openalex.org/W1972233422","https://openalex.org/W4385486824","https://openalex.org/W4297695714","https://openalex.org/W2611316230","https://openalex.org/W1528302882","https://openalex.org/W2274026817","https://openalex.org/W2612632602","https://openalex.org/W2321805087","https://openalex.org/W2296858511","https://openalex.org/W4403467802"],"abstract_inverted_index":{"Efficiently":[0],"compressing":[1],"high-dimensional":[2],"audio":[3,26,38,50,83,90,124,136,168,181,184,199],"signals":[4,91],"into":[5,85,92],"a":[6,48,61,150],"compact":[7],"and":[8,20,40,60,186],"informative":[9],"latent":[10,70],"space":[11],"is":[12],"crucial":[13],"for":[14,195],"various":[15],"tasks,":[16],"including":[17],"generative":[18],"modeling":[19],"music":[21],"information":[22],"retrieval":[23],"(MIR).":[24],"Existing":[25],"autoencoders,":[27],"however,":[28],"often":[29],"struggle":[30],"to":[31,64,111,163],"achieve":[32,112],"high":[33],"compression":[34,119],"ratios":[35],"while":[36],"preserving":[37],"fidelity":[39],"facilitating":[41],"efficient":[42],"downstream":[43,189],"applications.":[44],"We":[45],"introduce":[46],"Music2Latent2,":[47],"novel":[49,62,151],"autoencoder":[51],"that":[52,80,155,176],"addresses":[53],"these":[54],"limitations":[55],"by":[56],"leveraging":[57],"consistency":[58,130,161],"models":[59,162],"approach":[63],"representation":[65],"learning":[66],"based":[67],"on":[68,133,188],"unordered":[69],"embeddings,":[71,96],"which":[72],"we":[73,148],"call":[74],"summary":[75,95],"embeddings.":[76],"Unlike":[77],"conventional":[78],"methods":[79],"encode":[81],"local":[82],"features":[84,104],"ordered":[86],"sequences,":[87],"Music2Latent2":[88,126,177,191],"compresses":[89],"sets":[93],"of":[94,105,160],"where":[97],"each":[98],"embedding":[99],"can":[100],"capture":[101],"distinct":[102],"global":[103],"the":[106,117,157,166,193],"input":[107],"sample.":[108],"This":[109],"enables":[110],"higher":[113],"reconstruction":[114,143],"quality":[115,185],"at":[116,169],"same":[118],"ratio.":[120],"To":[121],"handle":[122],"arbitrary":[123],"lengths,":[125],"employs":[127],"an":[128],"autoregressive":[129],"model":[131],"trained":[132],"two":[134],"consecutive":[135],"chunks":[137],"with":[138],"causal":[139],"masking,":[140],"ensuring":[141],"coherent":[142],"across":[144],"segment":[145],"boundaries.":[146],"Additionally,":[147],"propose":[149],"two-step":[152],"decoding":[153],"procedure":[154],"leverages":[156],"denoising":[158],"capabilities":[159],"further":[164],"refine":[165],"generated":[167],"no":[170],"additional":[171],"cost.":[172],"Our":[173],"experiments":[174],"demonstrate":[175],"outperforms":[178],"existing":[179],"continuous":[180],"autoencoders":[182],"regarding":[183],"performance":[187],"tasks.":[190],"paves":[192],"way":[194],"new":[196],"possibilities":[197],"in":[198],"compression.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}