{"id":"https://openalex.org/W4386763523","doi":"https://doi.org/10.1109/waspaa58266.2023.10248118","title":"Leveraging Synthetic Data for Improving Chamber Ensemble Separation","display_name":"Leveraging Synthetic Data for Improving Chamber Ensemble Separation","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763523","doi":"https://doi.org/10.1109/waspaa58266.2023.10248118"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/89844/2/Sarkar%20Leveraging%20synthetic%20data%202023%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048735460","display_name":"Saurjya Sarkar","orcid":"https://orcid.org/0000-0002-9645-6525"},"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":"Saurjya Sarkar","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK","Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112012992","display_name":"Louise Thorpe","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":"Louise Thorpe","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK","Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","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":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK","Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076173089","display_name":"M. Sandler","orcid":"https://orcid.org/0000-0002-5691-8107"},"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":"Mark Sandler","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music,London,UK","Centre for Digital Music, Queen Mary University of London, London, UK"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music,London,UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music, Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048735460"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.5912,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65396511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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":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/T10860","display_name":"Speech 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/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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6518058180809021},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4474871754646301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4349032938480377},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.42610424757003784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3631334900856018},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33262449502944946},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22940942645072937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518058180809021},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4474871754646301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4349032938480377},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.42610424757003784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3631334900856018},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33262449502944946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22940942645072937},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/89844","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/89844","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/89844/2/Sarkar%20Leveraging%20synthetic%20data%202023%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/89844","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/89844","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/89844/2/Sarkar%20Leveraging%20synthetic%20data%202023%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386763523.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W2118774185","https://openalex.org/W2460742184","https://openalex.org/W2587061991","https://openalex.org/W2669032454","https://openalex.org/W2759171953","https://openalex.org/W2774707525","https://openalex.org/W2949756029","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2990594533","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3101943858","https://openalex.org/W3116770123","https://openalex.org/W3198508974","https://openalex.org/W3213726885","https://openalex.org/W4226153886","https://openalex.org/W4226300471","https://openalex.org/W4287688400","https://openalex.org/W4298310324","https://openalex.org/W4308860619","https://openalex.org/W4372259973","https://openalex.org/W6631117800","https://openalex.org/W6746914816","https://openalex.org/W6757632829","https://openalex.org/W6766320909","https://openalex.org/W6781725382","https://openalex.org/W6788137280","https://openalex.org/W6846753064","https://openalex.org/W7064316622"],"related_works":["https://openalex.org/W2071676784","https://openalex.org/W4292513318","https://openalex.org/W2287611352","https://openalex.org/W3037187668","https://openalex.org/W320684304","https://openalex.org/W1509352139","https://openalex.org/W4385464961","https://openalex.org/W4308092240","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"In":[0,43,86],"this":[1,87],"work,":[2],"we":[3,46,89],"tackle":[4],"the":[5,24,29,48,70,99,103,119],"challenging":[6],"problem":[7],"of":[8,61,69,190,216],"separating":[9,62],"mono-phonic":[10],"instrument":[11],"mixtures":[12,68,219],"found":[13],"in":[14,50,131,153,161],"chamber":[15,105,115,172],"music":[16],"from":[17,23,39,102,118,220],"monaural":[18],"recordings.":[19],"This":[20,73],"task":[21,30,74],"differs":[22],"Music":[25],"Demixing":[26],"Challenge":[27],"where":[28],"is":[31,59,75],"to":[32,79,133,163,229],"separate":[33,47],"vocals,":[34],"drums,":[35],"and":[36,82,94,109,184,210,223],"bass":[37],"stems":[38],"mastered":[40],"stereo":[41],"tracks.":[42],"our":[44,57,156,169,205],"task,":[45],"instruments":[49],"a":[51,91,134,177],"permutation":[52],"invariant":[53],"fashion":[54],"such":[55],"that":[56,203],"model":[58,206],"capable":[60],"any":[63],"two":[64],"monophonic":[65],"instruments,":[66],"including":[67],"same":[71],"instrument.":[72],"particularly":[76],"difficult":[77],"due":[78],"label":[80],"ambiguity":[81],"high":[83],"spectral":[84],"overlap.":[85],"paper,":[88],"present":[90],"pre-training":[92,204],"strategy":[93,152],"data":[95,123,157],"augmentation":[96,124,158],"pipeline":[97,159],"using":[98,113,126],"multi-mic":[100],"renders":[101],"synthetic":[104,127],"ensemble":[106,116,173],"dataset":[107],"EnsembleSet":[108],"evaluate":[110],"its":[111],"impact":[112],"real-world":[114],"recordings":[117],"URMP":[120],"dataset.":[121],"Our":[122,150],"pipeline,":[125],"data,":[128],"has":[129],"resulted":[130],"up":[132,162,228],"remarkable":[135],"+5.14":[136],"dB":[137,165,192,231],"cross-dataset":[138],"performance":[139,166,186,193],"improvement":[140,167,233],"for":[141,171,195,234],"time-domain":[142],"separation":[143,185,215],"models":[144],"when":[145],"tested":[146],"on":[147],"real":[148],"data.":[149],"fine-tuning":[151],"conjunction":[154],"with":[155,187,197,207,214,227],"results":[160],"+10.62":[164],"w.r.t.":[168],"baseline":[170],"separation.":[174],"We":[175,200],"report":[176],"strong":[178],"negative":[179],"correlation":[180],"between":[181],"pitch":[182,198],"overlap":[183],"an":[188],"average":[189],"5":[191],"drop":[194],"examples":[196],"overlaps.":[199],"also":[201],"show":[202],"string,":[208],"wind,":[209],"brass":[211],"ensembles":[212],"helps":[213],"vocal":[217,237],"harmony":[218,238],"Bach":[221],"Chorales":[222],"Barbershop":[224],"Quartet":[225],"datasets":[226],"+17.92":[230],"SI-SDR":[232],"2":[235],"source":[236],"mixtures.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}