{"id":"https://openalex.org/W3198234746","doi":"https://doi.org/10.21437/interspeech.2021-2260","title":"Neural Speaker Extraction with Speaker-Speech Cross-Attention Network","display_name":"Neural Speaker Extraction with Speaker-Speech Cross-Attention Network","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198234746","doi":"https://doi.org/10.21437/interspeech.2021-2260","mag":"3198234746"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-2260","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5006131727","display_name":"Wupeng Wang","orcid":"https://orcid.org/0009-0000-5360-2054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wupeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103210439","display_name":"Chenglin Xu","orcid":"https://orcid.org/0000-0002-1584-6282"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenglin Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071074013","display_name":"Meng Ge","orcid":"https://orcid.org/0000-0003-2017-4529"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Ge","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","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":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3535","last_page":"3539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.7600323557853699},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7211900949478149},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6338505744934082},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6130302548408508},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5340425372123718},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.46777310967445374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729709982872009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7600323557853699},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7211900949478149},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6338505744934082},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6130302548408508},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5340425372123718},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.46777310967445374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729709982872009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-2260","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-2260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1773016195","https://openalex.org/W1991139021","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2766901645","https://openalex.org/W2800022361","https://openalex.org/W2889418727","https://openalex.org/W2889540509","https://openalex.org/W2891405874","https://openalex.org/W2891833136","https://openalex.org/W2895807593","https://openalex.org/W2924115626","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2996428491","https://openalex.org/W3016010032","https://openalex.org/W3016129867","https://openalex.org/W3103434036"],"related_works":["https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975","https://openalex.org/W1940231550","https://openalex.org/W2118860825"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
