{"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","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-789","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/A5100358563","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0001-9056-291X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haoyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086417695","display_name":"Baochen Yang","orcid":"https://orcid.org/0000-0002-0494-0361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baochen Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103250176","display_name":"Yu Xi","orcid":"https://orcid.org/0000-0003-0498-0328"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085198169","display_name":"Linfeng Yu","orcid":"https://orcid.org/0000-0002-1548-5480"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linfeng Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tian Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100607010","display_name":"Hao Li","orcid":"https://orcid.org/0000-0001-6786-6501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100358563"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6528,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91191316,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9796000123023987,"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":0.9796000123023987,"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":0.9671000242233276,"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/keyword-spotting","display_name":"Keyword spotting","score":0.9323187470436096},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.7565000057220459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7295479774475098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7217081189155579},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46432796120643616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4590666592121124},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.410499632358551}],"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":1,"locations":[{"id":"doi:10.21437/interspeech.2024-789","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-789","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":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W4286904253","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}