{"id":"https://openalex.org/W4405710063","doi":"https://doi.org/10.1109/biocas61083.2024.10798276","title":"Two-Stage Cross-Modal Speech Separation Based on Speech Embeddings","display_name":"Two-Stage Cross-Modal Speech Separation Based on Speech Embeddings","publication_year":2024,"publication_date":"2024-10-24","ids":{"openalex":"https://openalex.org/W4405710063","doi":"https://doi.org/10.1109/biocas61083.2024.10798276"},"language":"en","primary_location":{"id":"doi:10.1109/biocas61083.2024.10798276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/biocas61083.2024.10798276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Biomedical Circuits and Systems Conference (BioCAS)","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/A5034561537","display_name":"Yuanjie Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanjie Deng","raw_affiliation_strings":["Shandong University,School of Control Science and Engineering,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Control Science and Engineering,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060046162","display_name":"Yinggang Liu","orcid":"https://orcid.org/0009-0006-7641-616X"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinggang Liu","raw_affiliation_strings":["Shandong University,School of Control Science and Engineering,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Control Science and Engineering,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032277221","display_name":"Ying Wei","orcid":"https://orcid.org/0000-0003-0743-6686"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wei","raw_affiliation_strings":["Shandong University Industrial Technology Research Institute of Shandong Province,Jinan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University Industrial Technology Research Institute of Shandong Province,Jinan,China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154099455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29400941,"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":0.9954000115394592,"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":0.9954000115394592,"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":0.9860000014305115,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.651509702205658},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6507126688957214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6167620420455933},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.476046085357666},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07189539074897766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.651509702205658},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6507126688957214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6167620420455933},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.476046085357666},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07189539074897766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/biocas61083.2024.10798276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/biocas61083.2024.10798276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Biomedical Circuits and Systems Conference (BioCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W189850294","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2291877678","https://openalex.org/W2808631503","https://openalex.org/W2952218014","https://openalex.org/W2962918445","https://openalex.org/W2962935966","https://openalex.org/W2963082324","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2972513594","https://openalex.org/W2973231102","https://openalex.org/W2979157532","https://openalex.org/W3000647100","https://openalex.org/W3008400075","https://openalex.org/W3010851250","https://openalex.org/W3015199127","https://openalex.org/W3015445830","https://openalex.org/W3015605047","https://openalex.org/W3015612952","https://openalex.org/W3020804303","https://openalex.org/W3024147341","https://openalex.org/W3096028031","https://openalex.org/W3136499730","https://openalex.org/W3160244659","https://openalex.org/W3160672713","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W4289846783","https://openalex.org/W6809919126"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"In":[0,78],"recent":[1],"years,":[2],"speech":[3,56,60,125],"separation":[4,57],"leveraging":[5],"visual":[6],"information":[7,39,97],"has":[8],"made":[9],"significant":[10],"progress.":[11],"To":[12,47],"enhance":[13],"the":[14,17,20,41,65,75,80,93,106,121],"focus":[15],"of":[16,67,90,103,124],"model":[18,94],"on":[19,31],"target":[21],"speaker,":[22],"several":[23],"studies":[24],"have":[25],"incorporated":[26],"additional":[27,38],"acoustic":[28],"features":[29,91],"based":[30],"audio-visual":[32],"fusion.":[33],"But":[34],"current":[35],"methods":[36],"require":[37],"about":[40],"speaker":[42,71],"to":[43,95],"extract":[44],"such":[45],"features.":[46],"address":[48],"this":[49],"limitation,":[50],"we":[51],"propose":[52],"a":[53,101],"two-stage":[54],"cross-modal":[55],"model,":[58],"whose":[59],"embeddings":[61],"extraction":[62],"module":[63],"avoids":[64],"need":[66],"pre-enrolled":[68],"voice":[69],"and":[70],"IDS,":[72],"thereby":[73],"expanding":[74],"method\u2019s":[76],"applicability.":[77],"addition,":[79],"proposed":[81],"multi-level":[82],"feature":[83],"fusion":[84],"can":[85],"fully":[86],"mine":[87],"different":[88],"levels":[89],"in":[92,105,119],"avoid":[96],"loss.":[98],"We":[99],"conduct":[100],"series":[102],"experiments":[104],"public":[107],"dataset":[108],"VoxCeleb2.":[109],"Compared":[110],"with":[111],"other":[112],"researches,":[113],"our":[114],"method":[115],"demonstrates":[116],"superior":[117],"performance":[118],"evaluating":[120],"key":[122],"indicators":[123],"separation.":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}