{"id":"https://openalex.org/W3169886170","doi":"https://doi.org/10.21437/interspeech.2021-1418","title":"A Hands-On Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation","display_name":"A Hands-On Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3169886170","doi":"https://doi.org/10.21437/interspeech.2021-1418","mag":"3169886170"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1418","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.09093","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050706599","display_name":"M. Strauss","orcid":"https://orcid.org/0000-0003-0610-8250"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Strauss","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054389422","display_name":"Jouni Paulus","orcid":"https://orcid.org/0000-0003-2283-2062"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jouni Paulus","raw_affiliation_strings":["Fraunhofer Society, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Society, Munich, Germany","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021417399","display_name":"Matteo Torcoli","orcid":"https://orcid.org/0000-0003-2834-9194"},"institutions":[{"id":"https://openalex.org/I4923324","display_name":"Fraunhofer-Gesellschaft","ror":"https://ror.org/05hkkdn48","country_code":"DE","type":"government","lineage":["https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matteo Torcoli","raw_affiliation_strings":["Fraunhofer Society, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Society, Munich, Germany","institution_ids":["https://openalex.org/I4923324"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022331149","display_name":"Bernd Edler","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Edler","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06185981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9998000264167786,"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":0.998199999332428,"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/dialog-box","display_name":"Dialog box","score":0.9006304740905762},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.8423442840576172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695869207382202},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6851540207862854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6465801000595093},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5792988538742065},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5028895735740662},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4944722652435303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46865028142929077},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4160858392715454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3006439208984375}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9006304740905762},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.8423442840576172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695869207382202},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6851540207862854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6465801000595093},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5792988538742065},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5028895735740662},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4944722652435303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46865028142929077},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4160858392715454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3006439208984375},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1418","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1418","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2106.09093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.09093","pdf_url":"https://arxiv.org/pdf/2106.09093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3169886170","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2106.09093v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:publica.fraunhofer.de:publica/417227","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/417227","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.2106.09093","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.09093","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.09093","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.09093","pdf_url":"https://arxiv.org/pdf/2106.09093","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3169886170.pdf","grobid_xml":"https://content.openalex.org/works/W3169886170.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1555479677","https://openalex.org/W2216465326","https://openalex.org/W2892356933","https://openalex.org/W2903502793","https://openalex.org/W2918296821","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963992487","https://openalex.org/W2964229681","https://openalex.org/W2968860202","https://openalex.org/W2972411915","https://openalex.org/W2972693890","https://openalex.org/W2975303551","https://openalex.org/W2975955714","https://openalex.org/W2979850772","https://openalex.org/W2990594533","https://openalex.org/W2998733532","https://openalex.org/W3001377302","https://openalex.org/W3003902031","https://openalex.org/W3009032512","https://openalex.org/W3037149862","https://openalex.org/W3093730058","https://openalex.org/W3101330598","https://openalex.org/W3108120840","https://openalex.org/W3115832427","https://openalex.org/W3123318516","https://openalex.org/W3145029257"],"related_works":["https://openalex.org/W3197676764","https://openalex.org/W3162629387","https://openalex.org/W2902132730","https://openalex.org/W2304609584","https://openalex.org/W2994988791","https://openalex.org/W2998657200","https://openalex.org/W3203028475","https://openalex.org/W3182939642","https://openalex.org/W2910254446","https://openalex.org/W3047886733","https://openalex.org/W3016067707","https://openalex.org/W3081753361","https://openalex.org/W2991037759","https://openalex.org/W3003231992","https://openalex.org/W3029444444","https://openalex.org/W3027465796","https://openalex.org/W2973165826","https://openalex.org/W2985045991","https://openalex.org/W2962715207","https://openalex.org/W3161305977"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,68,131,186],"hands-on":[4],"comparison":[5],"on":[6,92],"using":[7],"state-of-the-art":[8],"music":[9,35,64,93,165],"source":[10,166],"separation":[11,36,62,72,167,174],"deep":[12],"neural":[13],"networks":[14],"(DNNs)":[15],"before":[16,116],"and":[17,48,60,96,103,117,178],"after":[18,118],"task-specific":[19,190],"fine-tuning":[20,119],"for":[21,70,145,157,172],"separating":[22],"speech":[23,147],"content":[24,27],"from":[25,182],"non-speech":[26,139],"in":[28,63,73,100],"broadcast":[29,58,107],"audio":[30],"(i.e.,":[31],"dialog":[32,71,158,173],"separation).":[33],"The":[34,109,149,160],"models":[37,90,113,168],"are":[38,80,98],"selected":[39],"as":[40,67,127,129],"they":[41,180],"share":[42],"the":[43,56,74,87,101,112,138,183],"number":[44],"of":[45,111],"channels":[46],"(2)":[47],"sampling":[49],"rate":[50],"(44.1":[51],"kHz":[52],"or":[53],"higher)":[54],"with":[55,105,120,130],"considered":[57,66,99],"content,":[59],"vocals":[61],"is":[65,114,141],"parallel":[69],"target":[75],"application":[76,136],"domain.":[77],"These":[78],"similarities":[79],"assumed":[81],"to":[82,175,189],"enable":[83],"transfer":[84],"learning":[85],"between":[86],"tasks.":[88],"Three":[89],"pre-trained":[91,164],"(Open-Unmix,":[94],"Spleeter,":[95],"Conv-TasNet)":[97],"experiments,":[102],"fine-tuned":[104],"real":[106],"data.":[108],"performance":[110,187],"evaluated":[115],"computational":[121],"evaluation":[122],"metrics":[123],"(SI-SIRi,":[124],"SI-SDRi,":[125],"2f-model),":[126],"well":[128],"listening":[132],"test":[133],"simulating":[134],"an":[135],"where":[137],"signal":[140],"partially":[142],"attenuated,":[143],"e.g.,":[144],"better":[146],"intelligibility.":[148],"evaluations":[150],"include":[151],"two":[152],"reference":[153],"systems":[154],"specifically":[155],"developed":[156],"separation.":[159],"results":[161],"indicate":[162],"that":[163,179],"can":[169],"be":[170],"used":[171],"some":[176],"degree,":[177],"benefit":[181],"fine-tuning,":[184],"reaching":[185],"close":[188],"solutions.":[191]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2022-07-25T00:00:00"}