{"id":"https://openalex.org/W7148418289","doi":"https://doi.org/10.1109/asru65441.2025.11434627","title":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","display_name":"Low-Resource Domain Adaptation for Speech LLMs via Text-Only Fine-Tuning","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148418289","doi":"https://doi.org/10.1109/asru65441.2025.11434627"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434627","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/A5109489201","display_name":"Y. Y. Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yangui Fang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132798318","display_name":"Jing Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Peng","raw_affiliation_strings":["AI Institute, X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute, X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132790851","display_name":"Xu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I136848882","display_name":"Optech (Canada)","ror":"https://ror.org/03njz2k95","country_code":"CA","type":"company","lineage":["https://openalex.org/I136848882"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["AISpeech Co., Ltd,Suzhou,China"],"affiliations":[{"raw_affiliation_string":"AISpeech Co., Ltd,Suzhou,China","institution_ids":["https://openalex.org/I136848882"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801627","display_name":"Yu Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xi","raw_affiliation_strings":["AI Institute, X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute, X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767831","display_name":"Chengwei Zhang","orcid":"https://orcid.org/0000-0003-1620-4510"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengwei Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101083815","display_name":"Guohui Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohui Zhong","raw_affiliation_strings":["Huazhong University of Science and Technology,School of Electronic Information and Communications"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,School of Electronic Information and Communications","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132801590","display_name":"Kai Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["AI Institute, X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"AI Institute, X-LANCE Lab, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5109489201"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":4.3637,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95468031,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.930899977684021,"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":0.930899977684021,"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/T10028","display_name":"Topic Modeling","score":0.013500000350177288,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0071000000461936,"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/adaptation","display_name":"Adaptation (eye)","score":0.6940000057220459},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6628999710083008},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6105999946594238},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5928000211715698},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4902999997138977},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3758000135421753},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6940000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820999979972839},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5928000211715698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49540001153945923},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434627","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":[{"score":0.44689247012138367,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1995562189","https://openalex.org/W2077804127","https://openalex.org/W2079735306","https://openalex.org/W2171850596","https://openalex.org/W2403440562","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2940544976","https://openalex.org/W2963242190","https://openalex.org/W2972625221","https://openalex.org/W3097777922","https://openalex.org/W3198694222","https://openalex.org/W3200318528","https://openalex.org/W4225308107","https://openalex.org/W4283067311","https://openalex.org/W4316660917","https://openalex.org/W4385822246","https://openalex.org/W4385822295","https://openalex.org/W4389518985","https://openalex.org/W4391021395","https://openalex.org/W4391021545","https://openalex.org/W4392903288","https://openalex.org/W4392904149","https://openalex.org/W4392909790","https://openalex.org/W4393306207","https://openalex.org/W4410771025"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,33],"automatic":[3],"speech":[4,9],"recognition":[5,93],"(ASR)":[6],"have":[7],"combined":[8],"encoders":[10],"with":[11,21,95],"large":[12],"language":[13],"models":[14],"(LLMs)":[15],"through":[16],"projection,":[17],"forming":[18],"Speech":[19,49],"LLMs":[20,50],"strong":[22],"performance.":[23,79],"However,":[24],"adapting":[25],"them":[26],"to":[27,99,107],"new":[28,108],"domains":[29,109],"remains":[30],"challenging,":[31],"especially":[32],"low-resource":[34,120],"settings":[35],"where":[36],"paired":[37],"speech-text":[38,61],"data":[39],"is":[40],"scarce.":[41],"We":[42],"propose":[43],"a":[44,65],"text-only":[45,117],"fine-tuning":[46,118],"strategy":[47],"for":[48,119],"using":[51],"unpaired":[52],"target-domain":[53],"text":[54],"without":[55,110],"requiring":[56],"additional":[57],"audio.":[58],"To":[59],"preserve":[60],"alignment,":[62],"we":[63],"introduce":[64],"real-time":[66],"evaluation":[67],"mechanism":[68],"during":[69],"fine-tuning.":[70,102],"This":[71],"enables":[72],"effective":[73],"domain":[74,121],"adaptation":[75,122],"while":[76],"maintaining":[77],"source-domain":[78],"Experiments":[80],"on":[81],"LibriSpeech,":[82],"SlideSpeech,":[83],"and":[84],"Medical":[85],"datasets":[86],"show":[87],"that":[88],"our":[89],"method":[90],"achieves":[91],"competitive":[92],"performance,":[94],"minimal":[96],"degradation":[97],"compared":[98],"full":[100],"audio-text":[101],"It":[103],"also":[104],"improves":[105],"generalization":[106],"catastrophic":[111],"forgetting,":[112],"highlighting":[113],"the":[114],"potential":[115],"of":[116,123],"ASR.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}