{"id":"https://openalex.org/W4416249961","doi":"https://doi.org/10.1109/waspaa66052.2025.11230969","title":"Multi-Utterance Speech Separation and Association Trained on Short Segments","display_name":"Multi-Utterance Speech Separation and Association Trained on Short Segments","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416249961","doi":"https://doi.org/10.1109/waspaa66052.2025.11230969"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5011397847","display_name":"Yuzhu Wang","orcid":"https://orcid.org/0000-0002-4437-3111"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Yuzhu Wang","raw_affiliation_strings":["Tampere University,Signal Processing Research Center,Tampere,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Center,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Tampere University,Signal Processing Research Center,Tampere,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Center,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Nokia Technologies,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Espoo,Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Tampere University,Signal Processing Research Center,Tampere,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tampere University,Signal Processing Research Center,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011397847"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40059484,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.984499990940094,"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":0.984499990940094,"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":0.008200000040233135,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6266999840736389},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5496000051498413},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5475999712944031},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5396000146865845},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.5339999794960022},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4742000102996826},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4507000148296356},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42730000615119934},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.41040000319480896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476999759674072},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7236999869346619},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5339999794960022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5141000151634216},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.2840000092983246},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2752000093460083},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.25870001316070557},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25099998712539673},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/234113","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/234113","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2064364374","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2750259098","https://openalex.org/W2890964092","https://openalex.org/W2898268964","https://openalex.org/W2916618641","https://openalex.org/W2918296821","https://openalex.org/W2931364255","https://openalex.org/W2938358845","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3096893582","https://openalex.org/W3133834828","https://openalex.org/W3161201807","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3195010976","https://openalex.org/W3210390090","https://openalex.org/W4232282348","https://openalex.org/W4280592948","https://openalex.org/W4297841822","https://openalex.org/W4313417891","https://openalex.org/W4372271367","https://openalex.org/W4385756463","https://openalex.org/W4392903841","https://openalex.org/W4415433125"],"related_works":[],"abstract_inverted_index":{"Current":[0],"deep":[1],"neural":[2,62],"network":[3,63],"(DNN)":[4],"based":[5],"speech":[6,168],"separation":[7,110,169],"faces":[8],"a":[9,59,73,85],"fundamental":[10],"challenge":[11],"\u2014":[12],"while":[13,155],"the":[14,134,161],"models":[15,89],"need":[16],"to":[17,24,76],"be":[18],"trained":[19,98],"on":[20,99,146],"short":[21,100],"segments":[22,102,118],"due":[23],"computational":[25],"constraints,":[26],"real-world":[27],"applications":[28],"typically":[29],"require":[30],"processing":[31,112],"significantly":[32,114],"longer":[33,115],"recordings":[34],"with":[35],"multiple":[36],"utterances":[37],"per":[38],"speaker":[39,123,171],"than":[40,116],"seen":[41,130],"during":[42,131],"training.":[43,132],"In":[44],"this":[45,54,68],"paper,":[46],"we":[47],"investigate":[48],"how":[49],"existing":[50],"approaches":[51],"perform":[52],"in":[53,92],"challenging":[55],"scenario":[56],"and":[57,84,121,170],"propose":[58],"frequency-temporal":[60],"recurrent":[61],"(FTRNN)":[64],"that":[65,88],"effectively":[66],"bridges":[67],"gap.":[69],"Our":[70],"FTRNN":[71,165],"employs":[72],"full-band":[74],"module":[75,87],"model":[77,107],"frequency":[78,94],"dependencies":[79],"within":[80],"each":[81,93],"time":[82],"frame":[83],"sub-band":[86],"temporal":[90],"patterns":[91],"band.":[95],"Despite":[96],"being":[97],"fixed-length":[101],"of":[103,164],"10":[104],"s,":[105],"our":[106,138],"demonstrates":[108],"robust":[109],"when":[111],"signals":[113],"training":[117],"(21-121":[119],"s)":[120],"preserves":[122],"association":[124],"across":[125],"utterance":[126],"gaps":[127],"exceeding":[128],"those":[129],"Unlike":[133],"conventional":[135],"segment-separation-stitch":[136],"paradigm,":[137],"lightweight":[139],"approach":[140],"(0.9":[141],"M":[142],"parameters)":[143],"performs":[144],"inference":[145],"long":[147],"audio":[148],"without":[149],"segmentation,":[150],"eliminating":[151],"segment":[152],"boundary":[153],"distortions":[154],"simplifying":[156],"deployment.":[157],"Experimental":[158],"results":[159],"demonstrate":[160],"generalization":[162],"ability":[163],"for":[166],"multi-utterance":[167],"association.":[172]},"counts_by_year":[],"updated_date":"2026-05-01T08:36:08.643496","created_date":"2025-11-14T00:00:00"}