{"id":"https://openalex.org/W4402112442","doi":"https://doi.org/10.21437/interspeech.2024-225","title":"Target conversation extraction: Source separation using turn-taking dynamics","display_name":"Target conversation extraction: Source separation using turn-taking dynamics","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112442","doi":"https://doi.org/10.21437/interspeech.2024-225"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.11277","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091414943","display_name":"Tuochao Chen","orcid":"https://orcid.org/0000-0002-8031-5066"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuochao Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029531226","display_name":"Qirui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qirui Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107955160","display_name":"Bohan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohan Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035670633","display_name":"Malek Itani","orcid":"https://orcid.org/0009-0002-7249-2641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malek Itani","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106912759","display_name":"Emre Sefik Eskimez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emre Sefik Eskimez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011077730","display_name":"Shyamnath Gollakota","orcid":"https://orcid.org/0000-0002-9863-3054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shyamnath Gollakota","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5091414943"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3544,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66110592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3550","last_page":"3554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9944999814033508,"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/T12031","display_name":"Speech and dialogue systems","score":0.9668999910354614,"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/conversation","display_name":"Conversation","score":0.9402194023132324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402245998382568},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6825658679008484},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5408675074577332},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49272826313972473},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4703177511692047},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.4453135132789612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3800814747810364},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3478747606277466},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1728394329547882},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13377901911735535},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08320903778076172}],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.9402194023132324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402245998382568},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6825658679008484},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5408675074577332},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49272826313972473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4703177511692047},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.4453135132789612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3800814747810364},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3478747606277466},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1728394329547882},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13377901911735535},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08320903778076172},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2024-225","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2407.11277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.11277","pdf_url":"https://arxiv.org/pdf/2407.11277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.11277","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.11277","pdf_url":"https://arxiv.org/pdf/2407.11277","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6755165505","display_name":null,"funder_award_id":"award","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320333105","display_name":"CoMotion, University of Washington","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402112442.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2228992124","https://openalex.org/W2613954729","https://openalex.org/W3130118443","https://openalex.org/W1955947659","https://openalex.org/W2759378137","https://openalex.org/W2376974064","https://openalex.org/W3188579947","https://openalex.org/W4289529495","https://openalex.org/W4386695291","https://openalex.org/W2355699586"],"abstract_inverted_index":{"Extracting":[0],"the":[1,22,30,35,43,86,98],"speech":[2],"of":[3,25,37,46,48,88,100],"participants":[4],"in":[5,60,71,110],"a":[6,14,38,117],"conversation":[7,27,40,72,95],"amidst":[8],"interfering":[9,77,101],"speakers":[10,69,78],"and":[11,73,79,93,116],"noise":[12],"presents":[13],"challenging":[15],"problem.":[16],"In":[17,97],"this":[18],"paper,":[19],"we":[20,54,84],"introduce":[21],"novel":[23],"task":[24],"target":[26,39],"extraction,":[28],"where":[29],"goal":[31],"is":[32],"to":[33],"extract":[34],"audio":[36],"based":[41],"on":[42,91],"speaker":[44],"embedding":[45],"one":[47],"its":[49],"participants.":[50],"To":[51],"accomplish":[52],"this,":[53],"propose":[55],"leveraging":[56],"temporal":[57],"patterns":[58],"inherent":[59],"human":[61],"conversations,":[62],"particularly":[63],"turn-taking":[64],"dynamics,":[65],"which":[66],"uniquely":[67],"characterize":[68],"engaged":[70],"distinguish":[74],"them":[75],"from":[76],"noise.":[80],"Using":[81],"neural":[82],"networks,":[83],"show":[85,105],"feasibility":[87],"our":[89,103],"approach":[90],"English":[92],"Mandarin":[94],"datasets.":[96],"presence":[99],"speakers,":[102],"results":[104],"an":[106],"8.19":[107],"dB":[108,119],"improvement":[109,120],"signal-to-noise":[111],"ratio":[112],"for":[113,121],"2-speaker":[114],"conversations":[115],"7.92":[118],"2-4-speaker":[122],"conversations.":[123],"Code,":[124],"dataset":[125],"available":[126],"at":[127],"https://github.com/chentuochao/Target-Conversation-Extraction.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}