{"id":"https://openalex.org/W7148502656","doi":"https://doi.org/10.1109/asru65441.2025.11434808","title":"Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation","display_name":"Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148502656","doi":"https://doi.org/10.1109/asru65441.2025.11434808"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132805711","display_name":"Guo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guo Chen","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132813924","display_name":"Kai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006425914","display_name":"Runxuan Yang","orcid":"https://orcid.org/0009-0004-2526-1909"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runxuan Yang","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102014939","display_name":"Xiaolin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"BNRist, THBI, IDG/McGovern Institute for Brain Research, Tsinghua University,Department of Computer Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I144112489"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132805711"],"corresponding_institution_ids":["https://openalex.org/I144112489"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87573353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5752000212669373,"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":0.5752000212669373,"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":0.357699990272522,"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":0.007199999876320362,"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/cache","display_name":"Cache","score":0.683899998664856},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4973999857902527},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46709999442100525},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.429500013589859},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.3873000144958496},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3824999928474426},{"id":"https://openalex.org/keywords/episodic-memory","display_name":"Episodic memory","score":0.3635999858379364},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072999715805054},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.683899998664856},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4607999920845032},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3824999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3659000098705292},{"id":"https://openalex.org/C88576662","wikidata":"https://www.wikidata.org/wiki/Q18646","display_name":"Episodic memory","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.2831999957561493},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2784000039100647},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.26510000228881836},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.259799987077713},{"id":"https://openalex.org/C21963081","wikidata":"https://www.wikidata.org/wiki/Q11337567","display_name":"Working memory","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434808","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4522230923175812,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2035576074","https://openalex.org/W2127851351","https://openalex.org/W2460742184","https://openalex.org/W2889503488","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972541922","https://openalex.org/W3008283340","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3096571892","https://openalex.org/W3096893582","https://openalex.org/W3163652268","https://openalex.org/W4224938485","https://openalex.org/W4283021642","https://openalex.org/W4292387427","https://openalex.org/W4372271367","https://openalex.org/W4375869119","https://openalex.org/W4375869299","https://openalex.org/W4392904741"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"causal":[1,57,78],"speech":[2],"separation":[3],"models":[4,11],"often":[5],"under":[6],"perform":[7],"compared":[8],"to":[9,13,61,99],"non-causal":[10],"due":[12],"difficulties":[14],"in":[15],"retaining":[16],"historical":[17,45],"information.":[18],"To":[19],"address":[20],"this,":[21],"we":[22],"propose":[23],"the":[24,62,77,100,116],"Time-Frequency":[25],"Attention":[26],"Cache":[27],"Memory":[28],"(TFACM)":[29],"model,":[30,103],"which":[31],"effectively":[32],"captures":[33,53],"spatio-temporal":[34],"relationships":[35],"through":[36],"an":[37,50],"attention":[38,79],"mechanism":[39],"and":[40,67,76,108],"cache":[41],"memory":[42],"(CM)":[43],"for":[44,88],"information":[46],"storage.":[47],"In":[48],"TFACM,":[49],"LSTM":[51],"layer":[52],"frequency-relative":[54],"positions,":[55],"while":[56],"modeling":[58],"is":[59],"applied":[60],"time":[63],"dimension":[64],"using":[65],"local":[66],"global":[68],"representations.":[69],"The":[70],"CM":[71],"module":[72,82],"stores":[73],"past":[74],"information,":[75],"refinement":[80],"(CAR)":[81],"further":[83],"enhances":[84],"time-based":[85],"feature":[86],"representations":[87],"finer":[89],"granularity.":[90],"Experimental":[91],"results":[92],"showed":[93],"that":[94],"TFACM":[95],"achieved":[96],"comparable":[97],"performance":[98],"SOTA":[101],"TF-GridNet-Causal":[102],"with":[104],"significantly":[105],"lower":[106],"complexity":[107],"fewer":[109],"trainable":[110],"parameters.":[111],"For":[112],"more":[113],"details,":[114],"visit":[115],"project":[117],"page:":[118],"https://anonymous.4open.science/w/TFACM-Page/.":[119]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}