{"id":"https://openalex.org/W4297841801","doi":"https://doi.org/10.21437/interspeech.2022-526","title":"CyclicAugment: Speech Data Random Augmentation with Cosine Annealing Scheduler for Automatic Speech Recognition","display_name":"CyclicAugment: Speech Data Random Augmentation with Cosine Annealing Scheduler for Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841801","doi":"https://doi.org/10.21437/interspeech.2022-526"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-526","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101865881","display_name":"Zhihan Wang","orcid":"https://orcid.org/0009-0006-1247-5339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488580","display_name":"Feng Hou","orcid":"https://orcid.org/0000-0001-9660-8034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000331282","display_name":"Yuanhang Qiu","orcid":"https://orcid.org/0000-0002-3015-6829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanhang Qiu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100882020","display_name":"Zhizhong Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizhong Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033363489","display_name":"Satwinder Singh","orcid":"https://orcid.org/0000-0002-2555-075X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satwinder Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100694558","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0001-7117-2772"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9228,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75065328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3859","last_page":"3863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9968000054359436,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9703999757766724,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7588362693786621},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7030627131462097},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44264310598373413},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34967780113220215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588362693786621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7030627131462097},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44264310598373413},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34967780113220215}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-526","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-526","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2407342067","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2022-10-01T00:00:00"}