{"id":"https://openalex.org/W4415433091","doi":"https://doi.org/10.21437/interspeech.2025-2311","title":"Robust Vocal Intensity Prediction: Overcoming Dataset Bias with Pretrained Deep Models","display_name":"Robust Vocal Intensity Prediction: Overcoming Dataset Bias with Pretrained Deep Models","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433091","doi":"https://doi.org/10.21437/interspeech.2025-2311"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://cnrs.hal.science/hal-05359416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120093833","display_name":"Quentin Le Tellier","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Quentin Le Tellier","raw_affiliation_strings":["STL - Sciences et Technologies des Langues - LISN (France)"],"affiliations":[{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040179623","display_name":"Marc \u00c9vrard","orcid":"https://orcid.org/0000-0002-6276-8141"},"institutions":[{"id":"https://openalex.org/I4387152856","display_name":"Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique","ror":"https://ror.org/00rd81916","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I277688954","https://openalex.org/I4387152856"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc Evrard","raw_affiliation_strings":["STL - Sciences et Technologies des Langues - LISN (France)","LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507\r\nRue du Belv\u00e9d\u00e8re\r\n91405 Orsay cedex\r\net \r\nCampus Universitaire b\u00e2t 640\r\n1 rue Raimond Castaing\r\n91190 Gif-sur-Yvette - France)"],"affiliations":[{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (France)","institution_ids":[]},{"raw_affiliation_string":"LISN - Laboratoire Interdisciplinaire des Sciences du Num\u00e9rique (Campus Universitaire b\u00e2t 507\r\nRue du Belv\u00e9d\u00e8re\r\n91405 Orsay cedex\r\net \r\nCampus Universitaire b\u00e2t 640\r\n1 rue Raimond Castaing\r\n91190 Gif-sur-Yvette - France)","institution_ids":["https://openalex.org/I4387152856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010099253","display_name":"Albert Rilliard","orcid":"https://orcid.org/0000-0001-6490-2386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albert Rilliard","raw_affiliation_strings":["STL - Sciences et Technologies des Langues - LISN (France)"],"affiliations":[{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107173963","display_name":"Jean-Sylvain Li\u00e9nard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Sylvain Li\u00e9nard","raw_affiliation_strings":["STL - Sciences et Technologies des Langues - LISN (France)"],"affiliations":[{"raw_affiliation_string":"STL - Sciences et Technologies des Langues - LISN (France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5120093833"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16664064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1728","last_page":"1732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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":0.9951000213623047,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/intensity","display_name":"Intensity (physics)","score":0.34529998898506165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3043000102043152},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.299699991941452},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.24889999628067017},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22769999504089355}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619000196456909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5286999940872192},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4138999879360199},{"id":"https://openalex.org/C93038891","wikidata":"https://www.wikidata.org/wiki/Q1061524","display_name":"Intensity (physics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.24889999628067017},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22769999504089355},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.21969999372959137}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2311","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2311","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05359416v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-05359416","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.isca-archive.org/interspeech_2025/index.html","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05359416v1","is_oa":true,"landing_page_url":"https://cnrs.hal.science/hal-05359416","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.isca-archive.org/interspeech_2025/index.html","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}
