{"id":"https://openalex.org/W4415433150","doi":"https://doi.org/10.21437/interspeech.2025-1669","title":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis","display_name":"Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433150","doi":"https://doi.org/10.21437/interspeech.2025-1669"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1669","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1669","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/A5085413616","display_name":"Tianyi Xu","orcid":"https://orcid.org/0009-0001-5332-8881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028966140","display_name":"Hongjie Chen","orcid":"https://orcid.org/0009-0001-4607-9629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongjie Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434820","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0002-2618-5694"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751609","display_name":"Hang Lv","orcid":"https://orcid.org/0000-0003-3739-443X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv Hang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700900","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0001-6284-3044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076156013","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-0728-9017"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071699836","display_name":"Zhennan Lin","orcid":"https://orcid.org/0000-0003-3602-7881"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhennan Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068291428","display_name":"Yong Xiang Li","orcid":"https://orcid.org/0000-0002-7925-8949"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongxiang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3146,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93222862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"584","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9265999794006348,"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":0.9265999794006348,"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/training","display_name":"Training (meteorology)","score":0.6078000068664551},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.34290000796318054},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3386000096797943},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2922999858856201},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.29089999198913574},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.26910001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6193000078201294},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5442000031471252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40700000524520874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36309999227523804},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2639000117778778},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-1669","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1669","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-24T00:00:00"}
