{"id":"https://openalex.org/W4385822606","doi":"https://doi.org/10.21437/interspeech.2023-1109","title":"End to End Spoken Language Diarization with Wav2vec Embeddings","display_name":"End to End Spoken Language Diarization with Wav2vec Embeddings","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822606","doi":"https://doi.org/10.21437/interspeech.2023-1109"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1109","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1109","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":"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/A5013209021","display_name":"Jagabandhu Mishra","orcid":"https://orcid.org/0000-0003-1878-6286"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jagabandhu Mishra","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112980290","display_name":"Jayadev N Patil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jayadev N Patil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111024456","display_name":"Amartya Chowdhury","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amartya Chowdhury","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079497409","display_name":"Mahadeva Prasanna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahadeva Prasanna","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013209021"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5254,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71200598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"505"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.9695000052452087,"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/T12031","display_name":"Speech and dialogue systems","score":0.951200008392334,"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/computer-science","display_name":"Computer science","score":0.7239888310432434},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6354597210884094},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5158766508102417},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5010683536529541},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4399830400943756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4162607789039612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38364875316619873},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.36241549253463745},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.10925352573394775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7239888310432434},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6354597210884094},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5158766508102417},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5010683536529541},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4399830400943756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4162607789039612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38364875316619873},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36241549253463745},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.10925352573394775},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1109","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1109","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":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W2111874347","https://openalex.org/W3120512183","https://openalex.org/W2118860825","https://openalex.org/W1509309911","https://openalex.org/W2096510939","https://openalex.org/W2041797852","https://openalex.org/W1599425004","https://openalex.org/W1940231550"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}