{"id":"https://openalex.org/W7172015408","doi":"https://doi.org/10.1145/3774521.3774597","title":"Low SNR Speech Perception with HuBERT: A Discussion on Visual-Audio Fusion and Domain-Specific Modeling","display_name":"Low SNR Speech Perception with HuBERT: A Discussion on Visual-Audio Fusion and Domain-Specific Modeling","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W7172015408","doi":"https://doi.org/10.1145/3774521.3774597"},"language":null,"primary_location":{"id":"doi:10.1145/3774521.3774597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774597","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069015748","display_name":"Jayasree Saha","orcid":"https://orcid.org/0000-0002-0839-1849"},"institutions":[{"id":"https://openalex.org/I5847235","display_name":"University of Petroleum and Energy Studies","ror":"https://ror.org/04q2jes40","country_code":"IN","type":"education","lineage":["https://openalex.org/I5847235"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jayasree Saha","raw_affiliation_strings":["UPES, Bidholii Campus, Dehradun, India"],"raw_orcid":"https://orcid.org/0000-0002-0839-1849","affiliations":[{"raw_affiliation_string":"UPES, Bidholii Campus, Dehradun, India","institution_ids":["https://openalex.org/I5847235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007109424","display_name":"Vinay P. Namboodiri","orcid":"https://orcid.org/0000-0001-5262-9722"},"institutions":[{"id":"https://openalex.org/I51601045","display_name":"University of Bath","ror":"https://ror.org/002h8g185","country_code":"GB","type":"education","lineage":["https://openalex.org/I51601045"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"vinay Namboodiri","raw_affiliation_strings":["University of Bath, Bath, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-5262-9722","affiliations":[{"raw_affiliation_string":"University of Bath, Bath, United Kingdom","institution_ids":["https://openalex.org/I51601045"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053112307","display_name":"C. V. Jawahar","orcid":"https://orcid.org/0000-0001-6767-7057"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. V Jawahar","raw_affiliation_strings":["IIIT hyderabad, Hyderabad, India"],"raw_orcid":"https://orcid.org/0000-0001-6767-7057","affiliations":[{"raw_affiliation_string":"IIIT hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4366999864578247},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.39480000734329224},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.36309999227523804},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3425000011920929},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.28929999470710754},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2671999931335449}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.621399998664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5995000004768372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.492000013589859},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774521.3774597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774597","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774597","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1956021273","https://openalex.org/W2014621385","https://openalex.org/W2091930743","https://openalex.org/W2129877081","https://openalex.org/W2326115863","https://openalex.org/W2888868298","https://openalex.org/W2920977479","https://openalex.org/W2971840980","https://openalex.org/W2972513594","https://openalex.org/W2983423850","https://openalex.org/W3015356564","https://openalex.org/W3020804303","https://openalex.org/W3121016465","https://openalex.org/W3161223924","https://openalex.org/W3173767661","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225274946","https://openalex.org/W4253675902","https://openalex.org/W4283794587","https://openalex.org/W4312337341","https://openalex.org/W4312789614","https://openalex.org/W4385478414","https://openalex.org/W4392909818"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-08-01T00:00:00"}
