{"id":"https://openalex.org/W4412945352","doi":"https://doi.org/10.18653/v1/2025.acl-long.654","title":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","display_name":"Language-Codec: Bridging Discrete Codec Representations and Speech Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945352","doi":"https://doi.org/10.18653/v1/2025.acl-long.654"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.654","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.654","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113394692","display_name":"Minghui Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghui Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230918","display_name":"Jialong Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialong Zuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083611896","display_name":"Ziyue Karen Jiang","orcid":"https://orcid.org/0009-0007-4158-4689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyue Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104327296","display_name":"Dingdong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dingdong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052852146","display_name":"Hanting Wang","orcid":"https://orcid.org/0009-0003-4032-9257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanting Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102824958","display_name":"Hai Huang","orcid":"https://orcid.org/0000-0003-2812-6791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hai Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08882511,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13332","last_page":"13345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9161999821662903,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9161999821662903,"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/bridging","display_name":"Bridging (networking)","score":0.8275350332260132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7966653108596802},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.7884584665298462},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7834768891334534},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5209921002388},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.442979097366333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3904111385345459},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2475169599056244},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.13439345359802246},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.10258874297142029},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.04483857750892639}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8275350332260132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966653108596802},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.7884584665298462},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7834768891334534},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5209921002388},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.442979097366333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3904111385345459},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2475169599056244},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.13439345359802246},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.10258874297142029},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.04483857750892639}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.654","is_oa":false,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.654","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4252424250","https://openalex.org/W2370747337","https://openalex.org/W1890500690","https://openalex.org/W2133351881","https://openalex.org/W2157819213","https://openalex.org/W2205640666","https://openalex.org/W2382399415","https://openalex.org/W2369511196","https://openalex.org/W2163719598","https://openalex.org/W4241950017"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
