{"id":"https://openalex.org/W4402111748","doi":"https://doi.org/10.21437/interspeech.2024-1560","title":"Centroid Estimation with Transformer-Based Speaker Embedder for Robust Target Speaker Extraction","display_name":"Centroid Estimation with Transformer-Based Speaker Embedder for Robust Target Speaker Extraction","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111748","doi":"https://doi.org/10.21437/interspeech.2024-1560"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1560","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1560","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":"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/A5012083888","display_name":"Woon-Haeng Heo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Woon-Haeng Heo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038916503","display_name":"Joon\u2010Gyu Maeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joongyu Maeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001800801","display_name":"Yoseb Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoseb Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020960851","display_name":"Nam Hyun Cho","orcid":"https://orcid.org/0000-0002-7188-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Namhyun Cho","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012083888"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76079815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4333","last_page":"4337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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":0.9900000095367432,"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":0.9783999919891357,"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/speaker-verification","display_name":"Speaker verification","score":0.7341245412826538},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.6693464517593384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6568366885185242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5461035370826721},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48663339018821716},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46974995732307434},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44379252195358276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4166232645511627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4119437038898468},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14502912759780884}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7341245412826538},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.6693464517593384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6568366885185242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5461035370826721},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48663339018821716},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46974995732307434},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44379252195358276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4166232645511627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4119437038898468},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14502912759780884},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1560","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1560","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
