{"id":"https://openalex.org/W4385822384","doi":"https://doi.org/10.21437/interspeech.2023-1422","title":"Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator","display_name":"Unified Modeling of Multi-Talker Overlapped Speech Recognition and Diarization with a Sidecar Separator","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822384","doi":"https://doi.org/10.21437/interspeech.2023-1422"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1422","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5089153961","display_name":"Lingwei Meng","orcid":"https://orcid.org/0000-0003-1028-6017"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingwei Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062761975","display_name":"Jiawen Kang","orcid":"https://orcid.org/0000-0002-8218-3490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawen Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065896539","display_name":"Mingyu Cui","orcid":"https://orcid.org/0000-0001-9781-9407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyu Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen Meng","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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3467","last_page":"3471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9467999935150146,"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":0.9467999935150146,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.756591796875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145001888275146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6839946508407593},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.48050200939178467},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3608035147190094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3407133221626282}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.756591796875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145001888275146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839946508407593},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.48050200939178467},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3608035147190094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407133221626282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1422","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2162158162","https://openalex.org/W1521049138","https://openalex.org/W1509309911","https://openalex.org/W2144208207","https://openalex.org/W2175373321","https://openalex.org/W2499802997","https://openalex.org/W1497807607","https://openalex.org/W1813780412","https://openalex.org/W2128773298","https://openalex.org/W2160753975"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}