{"id":"https://openalex.org/W4403126636","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694531","title":"Robustness of Speech Separation Models for Similar-Pitch Speakers","display_name":"Robustness of Speech Separation Models for Similar-Pitch Speakers","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126636","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694531"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694531","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":"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/A5108781253","display_name":"B. Lay","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"B. Lay","raw_affiliation_strings":["Universität Hamburg Signal Processing"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg Signal Processing","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107580318","display_name":"Sebastian Zaczek","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Zaczek","raw_affiliation_strings":["Universität Hamburg Signal Processing"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg Signal Processing","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073497010","display_name":"Kristina Tesch","orcid":"https://orcid.org/0000-0002-6458-8128"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Tesch","raw_affiliation_strings":["Universität Hamburg Signal Processing"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg Signal Processing","institution_ids":["https://openalex.org/I4210121626"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087022569","display_name":"Timo Gerkmann","orcid":"https://orcid.org/0000-0002-8678-4699"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T. Gerkmann","raw_affiliation_strings":["Universität Hamburg Signal Processing"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg Signal Processing","institution_ids":["https://openalex.org/I4210121626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5108781253"],"corresponding_institution_ids":["https://openalex.org/I4210121626"],"apc_list":null,"apc_paid":null,"fwci":1.0336,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8114299,"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":"225","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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/T10860","display_name":"Speech and Audio Processing","score":0.9908999800682068,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9034000039100647,"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/robustness","display_name":"Robustness (evolution)","score":0.8177902698516846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7047677040100098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6844446659088135},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4302329123020172},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.415240615606308},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1032414436340332}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8177902698516846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7047677040100098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844446659088135},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4302329123020172},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.415240615606308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1032414436340332},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694531","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2024490156","https://openalex.org/W2118774185","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2552071709","https://openalex.org/W2891405874","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2972947281","https://openalex.org/W2981976899","https://openalex.org/W2998572311","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W4375869348","https://openalex.org/W4380434618","https://openalex.org/W4385245566","https://openalex.org/W4385823353","https://openalex.org/W4392903345","https://openalex.org/W6772349387"],"related_works":["https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Single-channel":[0],"speech":[1,9,123],"separation":[2,124],"is":[3],"a":[4,45,88],"crucial":[5],"task":[6],"for":[7,49,81,100],"enhancing":[8],"recognition":[10],"systems":[11],"in":[12,25],"multi-speaker":[13],"environments.":[14],"This":[15],"paper":[16],"investigates":[17],"the":[18,28,50,59,78,109,120],"robustness":[19],"of":[20,122],"state-of-the-art":[21],"Neural":[22,66],"Network":[23,67],"models":[24,74,97,125],"scenarios":[26],"where":[27],"pitch":[29,102],"differences":[30,103],"between":[31],"speakers":[32,128],"are":[33,112],"minimal.":[34],"Building":[35],"on":[36],"earlier":[37],"findings":[38,115],"by":[39],"Ditter":[40],"and":[41,64,84,129],"Gerkmann,":[42],"which":[43],"identified":[44],"significant":[46],"performance":[47,79,90,107],"drop":[48],"2018":[51],"Chimera++":[52],"under":[53,93],"similar-pitch":[54,127],"conditions,":[55,95],"our":[56],"study":[57],"extends":[58],"analysis":[60],"to":[61,126],"more":[62],"recent":[63],"sophisticated":[65],"models.":[68],"Our":[69],"experiments":[70],"reveal":[71],"that":[72],"modern":[73],"have":[75],"substantially":[76],"reduced":[77],"gap":[80,91],"matched":[82],"training":[83],"testing":[85],"conditions.":[86],"However,":[87],"substantial":[89],"persists":[92],"mismatched":[94],"with":[96],"performing":[98],"well":[99],"large":[101],"but":[104],"showing":[105],"worse":[106],"if":[108],"speakers\u2019":[110],"pitches":[111],"similar.":[113],"These":[114],"motivate":[116],"further":[117],"research":[118],"into":[119],"generalizability":[121],"unseen":[130],"data.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}