{"id":"https://openalex.org/W4410596136","doi":"https://doi.org/10.1016/j.csl.2025.101824","title":"Design choices for PixIT-based speaker-attributed ASR: Team ToTaTo at the NOTSOFAR-1 challenge","display_name":"Design choices for PixIT-based speaker-attributed ASR: Team ToTaTo at the NOTSOFAR-1 challenge","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410596136","doi":"https://doi.org/10.1016/j.csl.2025.101824"},"language":"en","primary_location":{"id":"doi:10.1016/j.csl.2025.101824","doi":"https://doi.org/10.1016/j.csl.2025.101824","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101824","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","erih-plus","jufo-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05084070","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","observed_orcids":["https://orcid.org/0000-0001-8224-513X"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joonas Kalda","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-8224-513X","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106914358","display_name":"S\u00e9verin Baroudi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e9verin Baroudi","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/A5044846779","display_name":"Martin Lebourdais","orcid":"https://orcid.org/0000-0001-7150-0588","observed_orcids":["https://orcid.org/0000-0001-7150-0588"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Lebourdais","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094077390","display_name":"Cl\u00e9ment Pag\u00e8s","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cl\u00e9ment Pag\u00e9s","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059","observed_orcids":["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","observed_orcids":["https://orcid.org/0000-0001-5083-1556"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanel Alum\u00e4e","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079257674","display_name":"Herv\u00e9 Bredin","orcid":"https://orcid.org/0000-0002-3739-925X","observed_orcids":["https://orcid.org/0000-0002-3739-925X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bredin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5084610587"],"corresponding_institution_ids":[],"apc_list":{"value":3530,"currency":"USD","value_usd":3530},"apc_paid":null,"fwci":0.2446,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50069465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"95","issue":null,"first_page":"101824","last_page":"101824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.9932000041007996,"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":0.006000000052154064,"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/T11309","display_name":"Music and Audio Processing","score":0.0003000000142492354,"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/permutation-invariant-training","display_name":"permutation invariant training","score":0.9520000219345093},{"id":"https://openalex.org/keywords/speech-separation","display_name":"speech separation","score":0.6230000257492065},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9490000009536743},{"id":"https://openalex.org/keywords/speaker-embedding","display_name":"speaker embedding","score":0.7509999871253967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8936475515365601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5172701478004456},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3633386492729187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33083510398864746}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.csl.2025.101824","doi":"https://doi.org/10.1016/j.csl.2025.101824","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.csl.2025.101824","pdf_url":null,"source":{"id":"https://openalex.org/S91252481","display_name":"Computer Speech & Language","issn_l":"0885-2308","issn":["0885-2308","1095-8363"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","dongbi-b","erih-plus","jufo-2","norway-2","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computer Speech &amp; Language","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05084070v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05084070","pdf_url":null,"source":{"id":"https://openalex.org/S4406922393","display_name":"HAL AMU","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Speech and Language, 2025, 95, pp.101824. &#x27E8;10.1016/j.csl.2025.101824&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05084070v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-05084070","pdf_url":null,"source":{"id":"https://openalex.org/S4406922393","display_name":"HAL AMU","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Speech and Language, 2025, 95, pp.101824. &#x27E8;10.1016/j.csl.2025.101824&#x27E9;","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3570594198","display_name":"Microscopic Intelligibility Modeling","funder_award_id":"ANR-20-CE23-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G4294119624","display_name":null,"funder_award_id":"2022 65 0079","funder_id":"https://openalex.org/F4320336678","funder_display_name":"Agence de l'innovation de D\u00e9fense"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321976","display_name":"Haridus- ja Teadusministeerium","ror":"https://ror.org/051aqjh92"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"},{"id":"https://openalex.org/F4320336678","display_name":"Agence de l'innovation de D\u00e9fense","ror":"https://ror.org/04mdawb03"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2125336414","https://openalex.org/W2222512263","https://openalex.org/W2563666542","https://openalex.org/W2590320937","https://openalex.org/W2792287754","https://openalex.org/W2800022361","https://openalex.org/W2896457183","https://openalex.org/W2900368655","https://openalex.org/W2917174945","https://openalex.org/W2933708090","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963341956","https://openalex.org/W3015199127","https://openalex.org/W3016232124","https://openalex.org/W3020336359","https://openalex.org/W3097777922","https://openalex.org/W3100954996","https://openalex.org/W3163842642","https://openalex.org/W3163903701","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W3206116612","https://openalex.org/W3207834622","https://openalex.org/W3209984917","https://openalex.org/W4226033575","https://openalex.org/W4234842379","https://openalex.org/W4319862481","https://openalex.org/W4375869348","https://openalex.org/W4389315122","https://openalex.org/W4389600306","https://openalex.org/W4392903251","https://openalex.org/W4400615784","https://openalex.org/W4402111631","https://openalex.org/W4402111989","https://openalex.org/W4402112083","https://openalex.org/W4402112099","https://openalex.org/W4402115971","https://openalex.org/W4403640501","https://openalex.org/W4408352169","https://openalex.org/W6796581206"],"related_works":["https://openalex.org/W4406347341","https://openalex.org/W4400615784","https://openalex.org/W4319586767","https://openalex.org/W7166639495","https://openalex.org/W4408346050","https://openalex.org/W2604869594","https://openalex.org/W4408703679","https://openalex.org/W4402111241","https://openalex.org/W3116025434","https://openalex.org/W2982269310"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-05-23T00:00:00"}
