{"id":"https://openalex.org/W4403126653","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694623","title":"Efficient Area-Based and Speaker-Agnostic Source Separation","display_name":"Efficient Area-Based and Speaker-Agnostic Source Separation","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126653","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694623"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5050706599","display_name":"M. Strauss","orcid":"https://orcid.org/0000-0003-0610-8250"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Strauss","raw_affiliation_strings":["International Audio Laboratories Erlangen,Erlangen,Germany,91058"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen,Erlangen,Germany,91058","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021837066","display_name":"Okan K\u00f6p\u00fckl\u00fc","orcid":"https://orcid.org/0000-0001-5281-9462"},"institutions":[{"id":"https://openalex.org/I4210087053","display_name":"Microsoft (Germany)","ror":"https://ror.org/001dd4s60","country_code":"DE","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210087053"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Okan K\u00f6p\u00fckl\u00fc","raw_affiliation_strings":["Microsoft,Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Munich,Germany","institution_ids":["https://openalex.org/I4210087053"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5659,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84538296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"185","last_page":"189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9923999905586243,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9449999928474426,"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":0.6957831382751465},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5674527883529663},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.519659161567688},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.4372292459011078},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38312751054763794},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15150675177574158},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09369313716888428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6957831382751465},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5674527883529663},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.519659161567688},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.4372292459011078},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38312751054763794},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15150675177574158},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09369313716888428},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W2168729028","https://openalex.org/W2763188033","https://openalex.org/W2885219692","https://openalex.org/W2952218014","https://openalex.org/W2963859210","https://openalex.org/W2964058413","https://openalex.org/W2991361823","https://openalex.org/W2997297221","https://openalex.org/W3097906045","https://openalex.org/W3160129476","https://openalex.org/W3163464523","https://openalex.org/W3207728800","https://openalex.org/W4294891356","https://openalex.org/W4296070366","https://openalex.org/W4312219134","https://openalex.org/W4372270656","https://openalex.org/W4372347386","https://openalex.org/W4375868926","https://openalex.org/W4388755868","https://openalex.org/W4392908343","https://openalex.org/W4395471087","https://openalex.org/W6757817989","https://openalex.org/W6784139575","https://openalex.org/W6839581590"],"related_works":["https://openalex.org/W1509813908","https://openalex.org/W2031820693","https://openalex.org/W3024816962","https://openalex.org/W973023320","https://openalex.org/W1910172735","https://openalex.org/W2118307209","https://openalex.org/W2107364365","https://openalex.org/W2539388437","https://openalex.org/W2107688514","https://openalex.org/W2137288760"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,21,46],"area-based":[4],"source":[5],"separation":[6,155],"method":[7,101],"designed":[8],"for":[9,52,119,153],"virtual":[10],"meeting":[11],"scenarios.":[12],"The":[13],"aim":[14],"is":[15,128],"to":[16,55,89,130,135],"preserve":[17],"speech":[18,103],"signals":[19],"from":[20,104],"unspecified":[22],"number":[23],"of":[24,33,114],"sources":[25,137],"within":[26,107,139],"a":[27,34,124,150],"defined":[28],"spatial":[29],"area":[30,110],"in":[31,147],"front":[32],"linear":[35],"microphone":[36],"array,":[37],"while":[38],"suppressing":[39],"all":[40],"other":[41],"sounds.":[42],"Therefore,":[43],"we":[44],"employ":[45],"efficient":[47],"neural":[48],"network":[49],"architecture":[50],"adapted":[51],"multi-channel":[53],"input":[54],"encompass":[56],"the":[57,63,99,108,132,140],"predefined":[58],"target":[59,73,109,141],"area.":[60,142],"To":[61],"evaluate":[62],"approach,":[64],"training":[65],"data":[66],"and":[67,74,91,156,160],"specific":[68],"test":[69],"scenarios":[70],"including":[71],"multiple":[72,105],"interfering":[75],"speakers,":[76],"as":[77,79],"well":[78],"background":[80],"noise":[81],"are":[82,86],"simulated.":[83],"All":[84],"models":[85],"rated":[87],"according":[88],"DNSMOS":[90],"scale-invariant":[92],"signal-to-distortion":[93],"ratio.":[94],"Our":[95],"experiments":[96],"show":[97],"that":[98],"proposed":[100],"separates":[102],"speakers":[106],"well,":[111],"besides":[112],"being":[113],"very":[115],"low":[116],"complexity,":[117],"intended":[118],"real-time":[120],"processing.":[121],"In":[122],"addition,":[123],"power":[125],"reduction":[126],"heatmap":[127],"used":[129],"demonstrate":[131],"networks\u2019":[133],"ability":[134],"identify":[136],"located":[138],"We":[143],"put":[144],"our":[145],"approach":[146],"context":[148],"with":[149],"well-established":[151],"baseline":[152],"speaker-speaker":[154],"discuss":[157],"its":[158],"strengths":[159],"challenges.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}