{"id":"https://openalex.org/W4372346433","doi":"https://doi.org/10.1109/icassp49357.2023.10094943","title":"Hyperbolic Audio Source Separation","display_name":"Hyperbolic Audio Source Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346433","doi":"https://doi.org/10.1109/icassp49357.2023.10094943"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5018337836","display_name":"Darius Petermann","orcid":"https://orcid.org/0000-0002-5973-5752"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Darius Petermann","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Department of Intelligent Systems Engineering, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Subramanian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"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":6,"citation_normalized_percentile":null,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/embedding","display_name":"Embedding","score":0.6531819701194763},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6290196180343628},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5016975402832031},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.488338440656662},{"id":"https://openalex.org/keywords/hyperbolic-function","display_name":"Hyperbolic function","score":0.4874532222747803},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.48341524600982666},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45094725489616394},{"id":"https://openalex.org/keywords/hyperbolic-space","display_name":"Hyperbolic space","score":0.44780197739601135},{"id":"https://openalex.org/keywords/hyperbolic-manifold","display_name":"Hyperbolic manifold","score":0.43078821897506714},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3699532747268677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3614356517791748},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3397899866104126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2446582317352295},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.15783634781837463},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09800410270690918}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6531819701194763},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6290196180343628},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5016975402832031},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.488338440656662},{"id":"https://openalex.org/C92047909","wikidata":"https://www.wikidata.org/wiki/Q204034","display_name":"Hyperbolic function","level":2,"score":0.4874532222747803},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.48341524600982666},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45094725489616394},{"id":"https://openalex.org/C83677898","wikidata":"https://www.wikidata.org/wiki/Q1878538","display_name":"Hyperbolic space","level":2,"score":0.44780197739601135},{"id":"https://openalex.org/C70984080","wikidata":"https://www.wikidata.org/wiki/Q2619102","display_name":"Hyperbolic manifold","level":3,"score":0.43078821897506714},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3699532747268677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3614356517791748},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3397899866104126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2446582317352295},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.15783634781837463},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09800410270690918},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":57,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W2127851351","https://openalex.org/W2164968193","https://openalex.org/W2199357291","https://openalex.org/W2221409856","https://openalex.org/W2735663686","https://openalex.org/W2797520557","https://openalex.org/W2806128501","https://openalex.org/W2891405874","https://openalex.org/W2903179019","https://openalex.org/W2936044260","https://openalex.org/W2948034225","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2984640634","https://openalex.org/W2998490864","https://openalex.org/W3015238983","https://openalex.org/W3015843733","https://openalex.org/W3023439819","https://openalex.org/W3035102141","https://openalex.org/W3090602628","https://openalex.org/W3099330747","https://openalex.org/W3106104628","https://openalex.org/W3124972797","https://openalex.org/W3127824945","https://openalex.org/W3153106544","https://openalex.org/W3168426623","https://openalex.org/W3173635498","https://openalex.org/W3173655578","https://openalex.org/W3186402624","https://openalex.org/W3213726885","https://openalex.org/W3216283037","https://openalex.org/W4226044115","https://openalex.org/W4226296142","https://openalex.org/W4226300471","https://openalex.org/W4287077834","https://openalex.org/W4288088482","https://openalex.org/W4294371460","https://openalex.org/W4312120655","https://openalex.org/W4313127305","https://openalex.org/W6617145748","https://openalex.org/W6751693566","https://openalex.org/W6756483922","https://openalex.org/W6763586092","https://openalex.org/W6766952790","https://openalex.org/W6770412516","https://openalex.org/W6777006615","https://openalex.org/W6779429662","https://openalex.org/W6784556544","https://openalex.org/W6786621524","https://openalex.org/W6788889872","https://openalex.org/W6795969292","https://openalex.org/W6798064515","https://openalex.org/W6798740242"],"related_works":["https://openalex.org/W3128228318","https://openalex.org/W4240041676","https://openalex.org/W2045336066","https://openalex.org/W4297783881","https://openalex.org/W4366330423","https://openalex.org/W4388640056","https://openalex.org/W1608408498","https://openalex.org/W4289286627","https://openalex.org/W2097408449","https://openalex.org/W2399450755"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,11,43,51,62,81],"framework":[3],"for":[4,46],"audio":[5],"source":[6,87],"separation":[7],"using":[8,57],"embeddings":[9],"on":[10],"hyperbolic":[12,38,44,58,76,120],"manifold":[13],"that":[14,101],"compactly":[15],"represent":[16],"the":[17,111,114,119],"hierarchical":[18,31],"relationship":[19],"between":[20,132],"sound":[21],"sources":[22,107],"and":[23,35,54,71,122,135],"time-frequency":[24,48,102],"features.":[25],"Inspired":[26],"by":[27],"recent":[28],"successes":[29],"modeling":[30],"relationships":[32],"in":[33,84],"text":[34],"images":[36],"with":[37,91],"embeddings,":[39],"our":[40,75],"algorithm":[41],"obtains":[42],"embedding":[45,96],"each":[47],"bin":[49],"of":[50,67,86,118],"mixture":[52],"signal":[53],"estimates":[55],"masks":[56],"softmax":[59],"layers.":[60],"On":[61],"synthetic":[63],"dataset":[64],"containing":[65,104],"mixtures":[66],"multiple":[68,105],"people":[69],"talking":[70],"musical":[72],"instruments":[73],"playing,":[74],"model":[77],"performed":[78],"comparably":[79],"to":[80,88,129],"Euclidean":[82],"baseline":[83],"terms":[85],"distortion":[89],"ratio,":[90],"stronger":[92],"performance":[93],"at":[94],"low":[95],"dimensions.":[97],"Furthermore,":[98],"we":[99,123],"find":[100],"regions":[103],"overlapping":[106],"are":[108],"embedded":[109],"towards":[110],"center":[112],"(i.e.,":[113],"most":[115],"uncertain":[116],"region)":[117],"space,":[121],"can":[124],"use":[125],"this":[126],"certainty":[127],"estimate":[128],"efficiently":[130],"trade-off":[131],"artifact":[133],"introduction":[134],"interference":[136],"reduction":[137],"when":[138],"isolating":[139],"individual":[140],"sounds.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}