{"id":"https://openalex.org/W4412945298","doi":"https://doi.org/10.18653/v1/2025.acl-long.682","title":"Recent Advances in Speech Language Models: A Survey","display_name":"Recent Advances in Speech Language Models: A Survey","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945298","doi":"https://doi.org/10.18653/v1/2025.acl-long.682"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.682","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.682","pdf_url":"https://aclanthology.org/2025.acl-long.682.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.682.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093784802","display_name":"Wenqian Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqian Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111361916","display_name":"Dianzhi Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dianzhi Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101038769","display_name":"Xiaoqi Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoqi Jiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027386336","display_name":"Ziqiao Meng","orcid":"https://orcid.org/0000-0002-0231-5992"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziqiao Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102854878","display_name":"Guangyan Zhang","orcid":"https://orcid.org/0000-0002-3480-5902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangyan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101685621","display_name":"Qichao Wang","orcid":"https://orcid.org/0009-0001-0448-1820"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qichao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Steven Y. Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steven Y. Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042251906","display_name":"Irwin King","orcid":"https://orcid.org/0000-0001-8106-6447"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irwin King","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":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13943","last_page":"13970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9200999736785889,"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":0.9200999736785889,"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/computer-science","display_name":"Computer science","score":0.6967874765396118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3632621169090271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3570128083229065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967874765396118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3632621169090271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3570128083229065}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.682","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.682","pdf_url":"https://aclanthology.org/2025.acl-long.682.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.682","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.682","pdf_url":"https://aclanthology.org/2025.acl-long.682.pdf","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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945298.pdf","grobid_xml":"https://content.openalex.org/works/W4412945298.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Wenqian":[0],"Cui,":[1],"Dianzhi":[2],"Yu,":[3],"Xiaoqi":[4],"Jiao,":[5],"Ziqiao":[6],"Meng,":[7],"Guangyan":[8],"Zhang,":[9],"Qichao":[10],"Wang,":[11],"Steven":[12],"Y.":[13],"Guo,":[14],"Irwin":[15],"King.":[16],"Proceedings":[17],"of":[18,23],"the":[19,24],"63rd":[20],"Annual":[21],"Meeting":[22],"Association":[25],"for":[26],"Computational":[27],"Linguistics":[28],"(Volume":[29],"1:":[30],"Long":[31],"Papers).":[32],"2025.":[33]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":10}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}
