{"id":"https://openalex.org/W7148490330","doi":"https://doi.org/10.1109/asru65441.2025.11434591","title":"Continual Pre-training for Codec-Based Speech LLMs: Balancing Understanding and Generation","display_name":"Continual Pre-training for Codec-Based Speech LLMs: Balancing Understanding and Generation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148490330","doi":"https://doi.org/10.1109/asru65441.2025.11434591"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132828531","display_name":"Jiatong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132822932","display_name":"Chunlei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132817459","display_name":"Jinchuan Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109447424","display_name":"Junrui Ni","orcid":"https://orcid.org/0009-0004-1666-3842"},"institutions":[{"id":"https://openalex.org/I308392441","display_name":"International University of the Caribbean","ror":"https://ror.org/02rv57d03","country_code":"JM","type":"education","lineage":["https://openalex.org/I308392441"]}],"countries":["JM"],"is_corresponding":false,"raw_author_name":"Junrui Ni","raw_affiliation_strings":["UIUC"],"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I308392441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801844","display_name":"Hao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132825101","display_name":"Shinji Watanabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["CMU"],"affiliations":[{"raw_affiliation_string":"CMU","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132812568","display_name":"Dong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5132828531"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87571534,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.629800021648407,"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":0.629800021648407,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.09539999812841415,"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/T12031","display_name":"Speech and dialogue systems","score":0.07530000060796738,"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/process","display_name":"Process (computing)","score":0.2793000042438507},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.2711000144481659},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.258899986743927},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.24240000545978546},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24070000648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6240000128746033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3531999886035919},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.24240000545978546},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24070000648498535},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.23839999735355377}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434591","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2799473636","https://openalex.org/W2963015836","https://openalex.org/W2963242190","https://openalex.org/W2963532001","https://openalex.org/W2972359262","https://openalex.org/W2997200074","https://openalex.org/W3095410713","https://openalex.org/W3180374548","https://openalex.org/W3196509775","https://openalex.org/W3198217962","https://openalex.org/W3198533616","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W3215615641","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4385570170","https://openalex.org/W4385822683","https://openalex.org/W4385823111","https://openalex.org/W4389524500","https://openalex.org/W4391021627","https://openalex.org/W4391021675","https://openalex.org/W4392902623","https://openalex.org/W4392904805","https://openalex.org/W4392909068","https://openalex.org/W4401246677","https://openalex.org/W4402111799","https://openalex.org/W4402118927","https://openalex.org/W4402670057","https://openalex.org/W4402670203","https://openalex.org/W4402672034","https://openalex.org/W4402683124","https://openalex.org/W4405974781","https://openalex.org/W4406461437","https://openalex.org/W4406461681","https://openalex.org/W4408351949","https://openalex.org/W4408352440","https://openalex.org/W4408353241","https://openalex.org/W4409362462","https://openalex.org/W4411119187","https://openalex.org/W4411119544","https://openalex.org/W4415433412","https://openalex.org/W7133219565","https://openalex.org/W7133229781"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"speech":[3,13,17,106],"language":[4],"models":[5],"(LLMs)":[6],"have":[7],"extended":[8],"textual":[9,37],"LLMs":[10],"to":[11,39],"the":[12,70],"domain,":[14],"but":[15],"balancing":[16],"understanding":[18,55],"and":[19,46,56,65,94],"generation":[20],"remains":[21],"challenging,":[22],"especially":[23],"with":[24],"codec-based":[25],"representations.":[26],"We":[27],"propose":[28],"a":[29,36,99],"continual":[30],"pre-training":[31],"(CPT)":[32],"framework":[33],"that":[34],"adapts":[35],"LLM":[38],"handle":[40],"codec-discretized":[41],"speech,":[42],"mitigating":[43],"modality":[44],"mismatch":[45],"preserving":[47],"linguistic":[48],"reasoning.":[49],"Our":[50],"unified":[51,105],"model":[52],"supports":[53],"both":[54],"generation,":[57],"achieving":[58],"strong":[59],"results":[60],"across":[61],"ASR,":[62],"TTS,":[63],"S2T-Trans,":[64],"S2S-Trans.":[66],"Notably,":[67],"we":[68],"present":[69],"first":[71],"end-to-end,":[72],"single-pass":[73],"S2S-Trans":[74],"system":[75],"using":[76],"only":[77],"neural":[78],"codec":[79],"tokens,":[80],"without":[81],"intermediate":[82],"transcriptions,":[83],"translations,":[84],"or":[85],"semantic":[86],"tokens.":[87],"CPT":[88],"proves":[89],"essential":[90],"for":[91,102],"crossmodal":[92],"alignment":[93],"task":[95],"generalization,":[96],"making":[97],"it":[98],"powerful":[100],"tool":[101],"building":[103],"robust,":[104],"LLMs.":[107]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}