{"id":"https://openalex.org/W4402111963","doi":"https://doi.org/10.21437/interspeech.2024-789","title":"Text-aware Speech Separation for Multi-talker Keyword Spotting","display_name":"Text-aware Speech Separation for Multi-talker Keyword Spotting","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111963","doi":"https://doi.org/10.21437/interspeech.2024-789"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-789","doi":"https://doi.org/10.21437/interspeech.2024-789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-789","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.12447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100358563","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0001-9056-291X","observed_orcids":["https://orcid.org/0000-0001-9056-291X","https://orcid.org/0009-0006-6312-0095"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086417695","display_name":"Baochen Yang","orcid":"https://orcid.org/0000-0002-0494-0361","observed_orcids":["https://orcid.org/0000-0002-0494-0361"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baochen Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103250176","display_name":"Yu Xi","orcid":"https://orcid.org/0000-0003-0498-0328","observed_orcids":["https://orcid.org/0000-0003-0498-0328"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085198169","display_name":"Linfeng Yu","orcid":"https://orcid.org/0000-0002-1548-5480","observed_orcids":["https://orcid.org/0000-0002-1548-5480"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linfeng Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607010","display_name":"Hao Li","orcid":"https://orcid.org/0000-0001-6786-6501","observed_orcids":["https://orcid.org/0000-0001-6786-6501"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826","observed_orcids":["https://orcid.org/0000-0002-7102-9826"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3837,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93945128,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.5351999998092651,"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":0.5351999998092651,"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":0.4595000147819519,"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":0.0019000000320374966,"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/speech-separation","display_name":"speech separation","score":0.8650000095367432},{"id":"https://openalex.org/keywords/multi-talker-speech","display_name":"multi-speaker speech","score":0.7990000247955322},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"keyword spotting","score":0.9940000176429749},{"id":"https://openalex.org/keywords/speaker-separation","display_name":"speaker separation","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9323187470436096},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.7565000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7295479774475098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7217081189155579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46432796120643616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4590666592121124},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.410499632358551}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2024-789","doi":"https://doi.org/10.21437/interspeech.2024-789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-789","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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:2406.12447","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12447","pdf_url":"https://arxiv.org/pdf/2406.12447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.12447","doi":"https://doi.org/10.48550/arxiv.2406.12447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.12447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.12447","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12447","pdf_url":"https://arxiv.org/pdf/2406.12447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111963.pdf","grobid_xml":"https://content.openalex.org/works/W4402111963.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385823400","https://openalex.org/W4387968129","https://openalex.org/W7204652268","https://openalex.org/W4402111546","https://openalex.org/W4400903566","https://openalex.org/W3176579201","https://openalex.org/W4391827435","https://openalex.org/W7134890259","https://openalex.org/W7128509598","https://openalex.org/W883669783"],"abstract_inverted_index":{"For":[0],"noisy":[1,19],"environments,":[2],"ensuring":[3],"the":[4,32,45,52,87,105,122,125],"robustness":[5],"of":[6,90,124],"keyword":[7,117],"spotting":[8],"(KWS)":[9],"systems":[10],"is":[11,40,49],"essential.":[12],"While":[13],"much":[14],"research":[15,85],"has":[16,23],"focused":[17],"on":[18,58,131],"KWS,":[20],"less":[21],"attention":[22],"been":[24],"paid":[25],"to":[26,50],"multi-talker":[27,38,75],"mixed":[28,116,133],"speech":[29,39,54,134],"scenarios.":[30],"Unlike":[31],"usual":[33],"cocktail":[34],"party":[35],"problem":[36],"where":[37],"separated":[41],"using":[42],"speaker":[43],"clues,":[44],"key":[46],"challenge":[47],"here":[48],"extract":[51],"target":[53],"for":[55,74],"KWS":[56,76],"based":[57],"text":[59],"clues.":[60],"To":[61],"address":[62],"it,":[63],"this":[64],"paper":[65],"proposes":[66],"a":[67,78],"novel":[68],"Text-aware":[69],"Permutation":[70],"Determinization":[71],"Training":[72],"method":[73],"with":[77],"clue-based":[79],"Speech":[80],"Separation":[81],"front-end":[82],"(TPDT-SS).":[83],"Our":[84],"highlights":[86],"critical":[88],"role":[89],"SS":[91],"front-ends":[92],"and":[93],"shows":[94,108],"that":[95],"incorporating":[96],"keyword-specific":[97],"clues":[98],"into":[99],"these":[100],"models":[101],"can":[102],"greatly":[103,120],"enhance":[104],"effectiveness.":[106],"TPDT-SS":[107],"remarkable":[109],"success":[110],"in":[111,115,136],"addressing":[112],"permutation":[113],"problems":[114],"speech,":[118],"thereby":[119],"boosting":[121],"performance":[123,138],"backend.":[126],"Additionally,":[127],"fine-tuning":[128],"our":[129],"system":[130],"unseen":[132],"results":[135],"further":[137],"improvement.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2024-09-02T00:00:00"}