{"id":"https://openalex.org/W4415432596","doi":"https://doi.org/10.21437/interspeech.2025-2683","title":"SQ-AST: A Transformer-Based Model for Speech Quality Prediction","display_name":"SQ-AST: A Transformer-Based Model for Speech Quality Prediction","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432596","doi":"https://doi.org/10.21437/interspeech.2025-2683"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2683","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2683","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052449152","display_name":"Wafaa Wardah","orcid":"https://orcid.org/0000-0001-6356-5314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wafaa Wardah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079624149","display_name":"Robert P. Spang","orcid":"https://orcid.org/0000-0001-6580-9060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert P. Spang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078045893","display_name":"Vincent Barriac","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Barriac","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055695569","display_name":"Jan Reimes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Reimes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088133485","display_name":"Anna Llagostera","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anna Llagostera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013879623","display_name":"Jens Berger","orcid":"https://orcid.org/0000-0002-8978-5099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jens Berger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075001284","display_name":"Sebastian M\u00f6ller","orcid":"https://orcid.org/0000-0003-3057-0760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian M\u00f6ller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81185268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2335","last_page":"2339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9732999801635742,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9732999801635742,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.904699981212616,"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/quality","display_name":"Quality (philosophy)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2745000123977661},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.263700008392334},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24869999289512634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5819000005722046},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40639999508857727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24869999289512634},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.24300000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23890000581741333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2683","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2683","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"}],"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":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}