{"id":"https://openalex.org/W4385823119","doi":"https://doi.org/10.21437/interspeech.2023-1556","title":"Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training","display_name":"Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823119","doi":"https://doi.org/10.21437/interspeech.2023-1556"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1556","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5017490346","display_name":"Gege Qi","orcid":"https://orcid.org/0000-0002-0032-6786"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gege Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102976060","display_name":"Yuefeng Chen","orcid":"https://orcid.org/0000-0003-0378-3103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuefeng Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051298007","display_name":"Xiaofeng Mao","orcid":"https://orcid.org/0000-0003-4486-556X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofeng Mao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188934","display_name":"Xiaojun Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojun Jia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043909623","display_name":"Ranjie Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranjie Duan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451786","display_name":"Rong Zhang","orcid":"https://orcid.org/0000-0002-2288-2847"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050108117","display_name":"Hui Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5017490346"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64934894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"561","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9921000003814697,"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":0.9921000003814697,"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":0.9804999828338623,"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/adversarial-system","display_name":"Adversarial system","score":0.8273974061012268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7736647129058838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7735519409179688},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6512595415115356},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45899727940559387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42183998227119446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3548521399497986}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8273974061012268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7736647129058838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7735519409179688},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6512595415115356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45899727940559387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42183998227119446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3548521399497986},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1556","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1556","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W4394050964","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W4285706568","https://openalex.org/W2551249631"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
