{"id":"https://openalex.org/W4400615784","doi":"https://doi.org/10.21437/odyssey.2024-17","title":"PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings","display_name":"PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4400615784","doi":"https://doi.org/10.21437/odyssey.2024-17"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2024-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2024-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04649858v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084610587","display_name":"Joonas Kalda","orcid":"https://orcid.org/0000-0001-8224-513X"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Joonas Kalda","raw_affiliation_strings":["TT\u00dc - Tallinn University of Technology (Ehitajate tee 5, 19086 Tallinn - Estonia)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TT\u00dc - Tallinn University of Technology (Ehitajate tee 5, 19086 Tallinn - Estonia)","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094077390","display_name":"Cl\u00e9ment Pag\u00e8s","orcid":null},"institutions":[{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cl\u00e9ment Pag\u00e9s","raw_affiliation_strings":["IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["DYNI - DYNamiques de l\u2019Information (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DYNI - DYNamiques de l\u2019Information (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023201445","display_name":"Tanel Alum\u00e4e","orcid":"https://orcid.org/0000-0001-5083-1556"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Tanel Alum\u00e4e","raw_affiliation_strings":["TT\u00dc - Tallinn University of Technology (Ehitajate tee 5, 19086 Tallinn - Estonia)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TT\u00dc - Tallinn University of Technology (Ehitajate tee 5, 19086 Tallinn - Estonia)","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bredin","raw_affiliation_strings":["IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)","IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)","CNRS - Centre National de la Recherche Scientifique (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT - Institut de recherche en informatique de Toulouse (118 Route de Narbonne, F-31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT\r\n118 Route de Narbonne\r\n31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210152422","https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I3131550300","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9943000078201294,"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":0.9943000078201294,"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":0.9478999972343445,"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/T10860","display_name":"Speech and Audio Processing","score":0.9398000240325928,"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-diarisation","display_name":"Speaker diarisation","score":0.8808265328407288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7231691479682922},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7062664031982422},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.696297824382782},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6278636455535889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3730693757534027},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07267114520072937}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8808265328407288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7231691479682922},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7062664031982422},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.696297824382782},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6278636455535889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3730693757534027},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07267114520072937},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2024-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2024-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04649858v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04649858","pdf_url":"https://hal.science/hal-04649858v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.isca-archive.org/odyssey_2024/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04649858v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04649858","pdf_url":"https://hal.science/hal-04649858v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.isca-archive.org/odyssey_2024/","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400615784.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2125336414","https://openalex.org/W2757672955","https://openalex.org/W2915347754","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972949456","https://openalex.org/W2974231335","https://openalex.org/W3008357631","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3093839391","https://openalex.org/W3163903701","https://openalex.org/W3167533889","https://openalex.org/W3178462146","https://openalex.org/W3196857193","https://openalex.org/W3206116612","https://openalex.org/W3209984917","https://openalex.org/W4287632494","https://openalex.org/W4292329485","https://openalex.org/W4311000453","https://openalex.org/W4319862481","https://openalex.org/W4319862697","https://openalex.org/W4372267974","https://openalex.org/W4372346876","https://openalex.org/W4385822293","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823318","https://openalex.org/W4390660238","https://openalex.org/W4402111989"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1813780412","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
