{"id":"https://openalex.org/W4388117238","doi":"https://doi.org/10.23919/eusipco58844.2023.10289800","title":"On Data Sampling Strategies for Training Neural Network Speech Separation Models","display_name":"On Data Sampling Strategies for Training Neural Network Speech Separation Models","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117238","doi":"https://doi.org/10.23919/eusipco58844.2023.10289800"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289800","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5004802529","display_name":"William Ravenscroft","orcid":"https://orcid.org/0000-0002-0780-3303"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"William Ravenscroft","raw_affiliation_strings":["The University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027797344","display_name":"Stefan Goetze","orcid":"https://orcid.org/0000-0003-1044-7343"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Goetze","raw_affiliation_strings":["The University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["The University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5004802529"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":1.0189,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.76807512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"335"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7646026611328125},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5824917554855347},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5612775087356567},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.46879467368125916},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46527099609375},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4577997028827667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44624489545822144},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4453813433647156},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43938177824020386},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4143572151660919},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4130347967147827},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40241941809654236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3392038345336914},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.14282923936843872},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13528281450271606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646026611328125},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5824917554855347},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5612775087356567},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.46879467368125916},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46527099609375},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4577997028827667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44624489545822144},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4453813433647156},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43938177824020386},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4143572151660919},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4130347967147827},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40241941809654236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3392038345336914},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.14282923936843872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13528281450271606},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289800","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1569512666","https://openalex.org/W2564013664","https://openalex.org/W2734774145","https://openalex.org/W2884797218","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W2972947281","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3037798801","https://openalex.org/W3086154751","https://openalex.org/W3094831814","https://openalex.org/W3099330747","https://openalex.org/W3133514748","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3213661887","https://openalex.org/W4280557595","https://openalex.org/W4296068774","https://openalex.org/W4312580459","https://openalex.org/W4372260572","https://openalex.org/W6768815455","https://openalex.org/W6779709467"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4313906399","https://openalex.org/W4321487865","https://openalex.org/W4321444604","https://openalex.org/W2811106690","https://openalex.org/W2936819511","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W2318112981","https://openalex.org/W4312417841"],"abstract_inverted_index":{"Speech":[0],"separation":[1,23,82],"remains":[2],"an":[3],"important":[4],"area":[5],"of":[6,26,54,69,103,141,159],"multi-speaker":[7],"signal":[8,73,104,178],"processing.":[9],"Deep":[10],"neural":[11],"network":[12],"(DNN)":[13],"models":[14,28],"have":[15,36],"attained":[16],"the":[17,52,67,138,142,169,181],"best":[18],"performance":[19,58],"on":[20,56,110],"many":[21],"speech":[22,81],"benchmarks.":[24],"Some":[25],"these":[27,49,71],"can":[29],"take":[30],"significant":[31],"time":[32,192],"to":[33,47,131,135,167],"train":[34],"and":[35,88,96,107,161,176],"high":[37],"memory":[38],"requirements.":[39],"Previous":[40],"work":[41],"has":[42],"proposed":[43],"shortening":[44],"training":[45,72,111,191],"examples":[46,148],"address":[48],"issues":[50],"but":[51],"impact":[53,68,109],"this":[55,65],"model":[57,153,172],"is":[59,77,114,129,165],"not":[60],"yet":[61],"well":[62],"understood.":[63],"In":[64],"work,":[66],"applying":[70,120],"length":[74,105],"(TSL)":[75],"limits":[76,123],"analysed":[78,100],"for":[79,117,149],"two":[80],"models:":[83],"SepFormer,":[84],"a":[85,90,156,187],"transformer":[86],"model,":[87],"Conv-TasNet,":[89],"convolutional":[91],"model.":[92],"The":[93],"WJS0-2Mix,":[94],"WHAMR":[95],"Libri2Mix":[97],"datasets":[98],"are":[99],"in":[101,125,145,186,190],"terms":[102],"distribution":[106],"its":[108],"efficiency.":[112],"It":[113],"demonstrated":[115],"that,":[116],"specific":[118,121],"distributions,":[119],"TSL":[122,157,183],"results":[124,185],"better":[126],"performance.":[127],"This":[128],"shown":[130,166],"be":[132],"mainly":[133],"due":[134],"randomly":[136],"sampling":[137],"start":[139],"index":[140],"waveforms":[143],"resulting":[144],"more":[146],"unique":[147],"training.":[150],"A":[151],"SepFormer":[152,171],"trained":[154,173],"using":[155],"limit":[158,184],"4.42s":[160,182],"dynamic":[162],"mixing":[163],"(DM)":[164],"match":[168],"best-performing":[170],"with":[174,193],"DM":[175],"unlimited":[177],"lengths.":[179],"Furthermore,":[180],"44%":[188],"reduction":[189],"WHAMR.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}