{"id":"https://openalex.org/W2972568703","doi":"https://doi.org/10.21437/interspeech.2019-1513","title":"Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues","display_name":"Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972568703","doi":"https://doi.org/10.21437/interspeech.2019-1513","mag":"2972568703"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1513","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070624983"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1863,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96375084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2718","last_page":"2722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.7837721109390259},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7638696432113647},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.598781943321228},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5032052397727966},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4926970303058624},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4320961534976959},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4218885898590088},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.15230798721313477},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07772201299667358}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837721109390259},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7638696432113647},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.598781943321228},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5032052397727966},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4926970303058624},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4320961534976959},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4218885898590088},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.15230798721313477},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07772201299667358}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1513","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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":13,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2398776621","https://openalex.org/W2734774145","https://openalex.org/W2891833136","https://openalex.org/W2901907199","https://openalex.org/W2939771864","https://openalex.org/W2949117887","https://openalex.org/W2963082324","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2964238697","https://openalex.org/W2964308564","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W2175373321","https://openalex.org/W1521049138","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1999004162","https://openalex.org/W4280634406"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8}],"updated_date":"2026-03-07T13:37:22.277990","created_date":"2025-10-10T00:00:00"}
