{"id":"https://openalex.org/W4375869129","doi":"https://doi.org/10.1109/icassp49357.2023.10095136","title":"Papez: Resource-Efficient Speech Separation with Auditory Working Memory","display_name":"Papez: Resource-Efficient Speech Separation with Auditory Working Memory","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869129","doi":"https://doi.org/10.1109/icassp49357.2023.10095136"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095136","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095136","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":"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/A5071732509","display_name":"Hyunseok Oh","orcid":"https://orcid.org/0000-0002-6127-561X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hyunseok Oh","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009621491","display_name":"Juheon Yi","orcid":"https://orcid.org/0000-0002-5080-7502"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juheon Yi","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100295770","display_name":"Youngki Lee","orcid":"https://orcid.org/0000-0002-6657-6059"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngki Lee","raw_affiliation_strings":["Seoul National University"],"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071732509"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.6113,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63517997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"34","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":0.9988999962806702,"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":0.9987000226974487,"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":0.8404639959335327},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.539412796497345},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5104705095291138},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4380803108215332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40148454904556274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17799273133277893},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16404250264167786},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10093000531196594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8404639959335327},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.539412796497345},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5104705095291138},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4380803108215332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40148454904556274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17799273133277893},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16404250264167786},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10093000531196594},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095136","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095136","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":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2019264110","https://openalex.org/W2025164243","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2231147640","https://openalex.org/W2276626389","https://openalex.org/W2325237720","https://openalex.org/W2338571620","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2866343820","https://openalex.org/W2891405874","https://openalex.org/W2908510526","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2981436548","https://openalex.org/W3006683367","https://openalex.org/W3015199127","https://openalex.org/W3027008958","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3105238007","https://openalex.org/W3160903688","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3214142715","https://openalex.org/W4283727958","https://openalex.org/W4287704453","https://openalex.org/W4296068589","https://openalex.org/W4296068774","https://openalex.org/W4385245566","https://openalex.org/W6701498492","https://openalex.org/W6739901393","https://openalex.org/W6753640285","https://openalex.org/W6757817989","https://openalex.org/W6774054309","https://openalex.org/W6777776875","https://openalex.org/W6781533629","https://openalex.org/W6796707148","https://openalex.org/W6803594737"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2370917603","https://openalex.org/W2390279801","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2358668433","https://openalex.org/W2347897961","https://openalex.org/W2981757109"],"abstract_inverted_index":{"Transformer-based":[0],"models":[1],"recently":[2],"reached":[3],"state-of-the-art":[4],"single-channel":[5,34],"speech":[6,35],"separation":[7,36],"accuracy;":[8],"However,":[9],"their":[10],"extreme":[11],"computational":[12],"load":[13],"makes":[14],"it":[15],"difficult":[16],"to":[17],"deploy":[18],"them":[19],"in":[20],"resource-constrained":[21],"mobile":[22],"or":[23],"IoT":[24],"devices.":[25],"We":[26,45,97],"thus":[27],"present":[28],"Papez,":[29],"a":[30,94],"lightweight":[31],"and":[32,90],"computation-efficient":[33],"model.":[37],"Papez":[38,85],"is":[39],"based":[40],"on":[41],"three":[42],"key":[43],"techniques.":[44],"first":[46],"replace":[47],"the":[48,60,72,77,87],"inter-chunk":[49],"Transformer":[50],"with":[51,93],"small-sized":[52],"auditory":[53],"working":[54],"memory.":[55],"Second,":[56],"we":[57,70],"adaptively":[58],"prune":[59],"input":[61],"tokens":[62],"that":[63,84],"do":[64],"not":[65],"need":[66],"further":[67],"processing.":[68],"Finally,":[69],"reduce":[71],"number":[73],"of":[74],"parameters":[75],"through":[76],"recurrent":[78],"transformer.":[79],"Our":[80],"extensive":[81],"evaluation":[82],"shows":[83],"achieves":[86],"best":[88],"resource":[89],"accuracy":[91],"tradeoffs":[92],"large":[95],"margin.":[96],"publicly":[98],"share":[99],"our":[100],"source":[101],"code":[102],"at":[103],"https://github.com/snuhcs/Papez.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}