{"id":"https://openalex.org/W6992963094","doi":null,"title":"Multimodal Speech Separation with Feedback Architecture","display_name":"Multimodal Speech Separation with Feedback Architecture","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W6992963094"},"language":"en","primary_location":{"id":"pmh:oai:jyx.jyu.fi:123456789/102963","doi":null,"is_oa":true,"landing_page_url":"http://urn.fi/URN:NBN:fi:jyu-202506024772","pdf_url":"https://jyx.jyu.fi/bitstreams/e41ed924-209b-4063-ad24-36497cd5529c/download","source":{"id":"https://openalex.org/S4306400563","display_name":"Jyv\u00e4skyl\u00e4 University Digital Archive (University of Jyv\u00e4skyl\u00e4)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I94722563","host_organization_name":"University of Jyv\u00e4skyl\u00e4","host_organization_lineage":["https://openalex.org/I94722563"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://jyx.jyu.fi/bitstreams/e41ed924-209b-4063-ad24-36497cd5529c/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qu, Yanren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94722563","display_name":"University of Jyv\u00e4skyl\u00e4","ror":"https://ror.org/05n3dz165","country_code":"FI","type":"education","lineage":["https://openalex.org/I94722563"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Qu, Yanren","raw_affiliation_strings":["University of Jyv\u00e4skyl\u00e4 Faculty of Information Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Jyv\u00e4skyl\u00e4 Faculty of Information Technology","institution_ids":["https://openalex.org/I94722563"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I94722563"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9330999851226807,"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":0.9330999851226807,"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":0.05180000141263008,"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":0.013500000350177288,"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/incremental-inference","display_name":"incremental inference","score":0.7960000038146973},{"id":"https://openalex.org/keywords/gpu-memory-efficiency","display_name":"GPU memory efficiency","score":0.7599999904632568},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603999972343445},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6277999877929688},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43849998712539673},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.26190000772476196},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:jyx.jyu.fi:123456789/102963","doi":null,"is_oa":true,"landing_page_url":"http://urn.fi/URN:NBN:fi:jyu-202506024772","pdf_url":"https://jyx.jyu.fi/bitstreams/e41ed924-209b-4063-ad24-36497cd5529c/download","source":{"id":"https://openalex.org/S4306400563","display_name":"Jyv\u00e4skyl\u00e4 University Digital Archive (University of Jyv\u00e4skyl\u00e4)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I94722563","host_organization_name":"University of Jyv\u00e4skyl\u00e4","host_organization_lineage":["https://openalex.org/I94722563"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"}],"best_oa_location":{"id":"pmh:oai:jyx.jyu.fi:123456789/102963","doi":null,"is_oa":true,"landing_page_url":"http://urn.fi/URN:NBN:fi:jyu-202506024772","pdf_url":"https://jyx.jyu.fi/bitstreams/e41ed924-209b-4063-ad24-36497cd5529c/download","source":{"id":"https://openalex.org/S4306400563","display_name":"Jyv\u00e4skyl\u00e4 University Digital Archive (University of Jyv\u00e4skyl\u00e4)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I94722563","host_organization_name":"University of Jyv\u00e4skyl\u00e4","host_organization_lineage":["https://openalex.org/I94722563"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6992963094.pdf","grobid_xml":"https://content.openalex.org/works/W6992963094.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1531333757","https://openalex.org/W2064675550","https://openalex.org/W2107878631","https://openalex.org/W2950635152","https://openalex.org/W2952218014","https://openalex.org/W3015199127","https://openalex.org/W3015636705","https://openalex.org/W3030163527","https://openalex.org/W3042857426","https://openalex.org/W3123221884","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3168867926","https://openalex.org/W3176906074","https://openalex.org/W4289304001","https://openalex.org/W4289665794","https://openalex.org/W4322718191","https://openalex.org/W4377865076","https://openalex.org/W4392904741","https://openalex.org/W4392909101","https://openalex.org/W4404782921","https://openalex.org/W4405634780","https://openalex.org/W4408353160","https://openalex.org/W4413157351"],"related_works":["https://openalex.org/W7078600024","https://openalex.org/W4392904741","https://openalex.org/W4415708977","https://openalex.org/W7166104007","https://openalex.org/W7155175589","https://openalex.org/W4297924644","https://openalex.org/W6979287192","https://openalex.org/W7167268745","https://openalex.org/W4393943345","https://openalex.org/W4415428356"],"abstract_inverted_index":{"This":[0],"thesis":[1],"tackles":[2],"the":[3,21],"high":[4],"computational":[5,105],"cost,":[6],"and":[7,45,90,116],"output":[8],"inconsistency":[9],"of":[10],"processing":[11,111],"long":[12],"audio":[13,39],"sequences":[14],"in":[15,92],"multimodal":[16,126],"speech":[17,127],"separation.":[18,128],"We":[19],"introduce":[20],"Self-Feedback":[22],"RE-Sepformer":[23,34],"(SFRS),":[24],"an":[25,28,66],"architecture":[26],"integrating":[27],"RNN-inspired":[29],"incremental":[30],"inference":[31,79],"mechanism":[32],"with":[33],"backbone.":[35],"SFRS":[36,60,71,107],"processes":[37],"non-overlapping":[38],"chunks,":[40],"using":[41],"propagated":[42],"hidden":[43],"states":[44],"previous":[46],"masks":[47],"as":[48],"feedback,":[49],"guided":[50],"by":[51,104],"strategically":[52],"fused":[53],"textual":[54],"embeddings.":[55],"Experiments":[56],"on":[57],"TextrolMix":[58],"show":[59],"achieves":[61],"10.8":[62],"dB":[63],"SI-SDRi,":[64],"outperforming":[65],"LLM-TSE":[67],"baseline.":[68],"In":[69],"addition,":[70],"demonstrates":[72],"substantial":[73],"GPU":[74],"memory":[75,114],"savings,":[76],"especially":[77],"during":[78],"(~7.2":[80],"GB":[81,84,95],"vs.":[82,96],"~27.5":[83],"for":[85,123],"a":[86,120],"comparable":[87],"non-incremental":[88],"approach)":[89],"also":[91],"training":[93],"(~20.2":[94],"~33.6":[97],"GB).":[98],"While":[99],"full":[100],"convergence":[101],"was":[102],"limited":[103],"constraints,":[106],"effectively":[108],"mitigates":[109],"long-sequence":[110],"burdens,":[112],"reduces":[113],"usage,":[115],"enhances":[117],"consistency,":[118],"offering":[119],"promising":[121],"path":[122],"efficient,":[124],"context-aware":[125]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}