{"id":"https://openalex.org/W4375869047","doi":"https://doi.org/10.1109/icassp49357.2023.10096684","title":"Multi-Resolution Location-Based Training for Multi-Channel Continuous Speech Separation","display_name":"Multi-Resolution Location-Based Training for Multi-Channel Continuous Speech Separation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869047","doi":"https://doi.org/10.1109/icassp49357.2023.10096684"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hassan Taherian","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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":0.9993000030517578,"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":0.9983000159263611,"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":0.7648487091064453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6710692644119263},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6276006698608398},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6135135889053345},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5215511322021484},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4854050576686859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42306554317474365},{"id":"https://openalex.org/keywords/resolution","display_name":"Resolution (logic)","score":0.41351717710494995},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4016430974006653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13604506850242615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648487091064453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6710692644119263},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6276006698608398},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6135135889053345},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5215511322021484},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4854050576686859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42306554317474365},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.41351717710494995},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4016430974006653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13604506850242615},{"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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2117678320","https://openalex.org/W2291877678","https://openalex.org/W2763188033","https://openalex.org/W2962866211","https://openalex.org/W2972460025","https://openalex.org/W3007256793","https://openalex.org/W3016232124","https://openalex.org/W3035268204","https://openalex.org/W3094831814","https://openalex.org/W3162863443","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3187990717","https://openalex.org/W3209238651","https://openalex.org/W3210134537","https://openalex.org/W4210402803","https://openalex.org/W4226016254","https://openalex.org/W4294891356","https://openalex.org/W4296068764","https://openalex.org/W4296069268","https://openalex.org/W6774995033"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2791440692"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,27],"automatic":[3],"speech":[4,12,18],"recognition":[5],"(ASR)":[6],"systems":[7],"severely":[8],"degrades":[9],"when":[10],"multi-talker":[11],"overlap":[13],"occurs.":[14],"In":[15],"meeting":[16],"environments,":[17],"separation":[19],"is":[20],"typically":[21],"performed":[22],"to":[23,67,76,83],"improve":[24],"the":[25,78,116],"robustness":[26],"ASR":[28],"systems.":[29],"Recently,":[30],"location-based":[31],"training":[32,39,54],"(LBT)":[33],"was":[34],"proposed":[35],"as":[36],"a":[37],"new":[38],"criterion":[40],"for":[41],"multi-channel":[42,69],"talker-independent":[43],"speaker":[44,70,99],"separation.":[45,71],"Assuming":[46],"fixed":[47],"array":[48],"geometry,":[49],"LBT":[50,66,75,109],"outperforms":[51,111],"widely-used":[52],"permutation-invariant":[53],"in":[55,101],"fully":[56],"overlapped":[57],"utterances":[58],"and":[59,86],"matched":[60],"reverberant":[61],"conditions.":[62],"This":[63],"paper":[64],"extends":[65],"conversational":[68],"We":[72],"introduce":[73],"multi-resolution":[74,90,108],"estimate":[77],"complex":[79],"spectrograms":[80],"from":[81],"low":[82],"high":[84],"time":[85],"frequency":[87],"resolutions.":[88],"With":[89],"LBT,":[91],"convolutional":[92],"kernels":[93],"are":[94],"assigned":[95],"consistently":[96,110],"based":[97],"on":[98,115],"locations":[100],"physical":[102],"space.":[103],"Evaluation":[104],"results":[105],"show":[106],"that":[107],"other":[112],"competitive":[113],"methods":[114],"recorded":[117],"LibriCSS":[118],"corpus.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}