{"id":"https://openalex.org/W4416251564","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229410","title":"Denoising GER: A Noise-Robust Generative Error Correction with LLM for Speech Recognition","display_name":"Denoising GER: A Noise-Robust Generative Error Correction with LLM for Speech Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251564","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229410"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100416810","display_name":"Yanyan Liu","orcid":"https://orcid.org/0000-0002-1405-7345"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Liu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413867","display_name":"Minqiang Xu","orcid":"https://orcid.org/0000-0003-3625-1736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minqiang Xu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101732743","display_name":"Yihao Chen","orcid":"https://orcid.org/0009-0009-9484-9956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Chen","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067399917","display_name":"Liang He","orcid":"https://orcid.org/0000-0003-2218-005X"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044739051","display_name":"Lei Fang","orcid":"https://orcid.org/0000-0002-1438-2500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sian Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sian Fang","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037906509","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0003-4173-7650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["Hefei iFly Digital Technology Co. Ltd.,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei iFly Digital Technology Co. Ltd.,Hefei,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8082000017166138,"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":0.8082000017166138,"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/T10860","display_name":"Speech and Audio Processing","score":0.14249999821186066,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.014600000344216824,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.654699981212616},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.611299991607666},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5557000041007996},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4242999851703644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4187999963760376},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41850000619888306},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.38089999556541443},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3693999946117401},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.365200012922287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795000076293945},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.654699981212616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6114000082015991},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.611299991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6047000288963318},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5557000041007996},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4242999851703644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41850000619888306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36169999837875366},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.326200008392334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2024490156","https://openalex.org/W2939111082","https://openalex.org/W2963240019","https://openalex.org/W3011339933","https://openalex.org/W4221156109","https://openalex.org/W4292595872","https://openalex.org/W4320495408","https://openalex.org/W4382240079","https://openalex.org/W4385822949","https://openalex.org/W4389520395","https://openalex.org/W4389524500","https://openalex.org/W4391021623","https://openalex.org/W4391021666","https://openalex.org/W4392903921","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4400447328","https://openalex.org/W4400903651","https://openalex.org/W4402112487","https://openalex.org/W4402670837"],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"large":[3],"language":[4],"models":[5],"(LLM)":[6],"have":[7],"made":[8],"significant":[9],"progress":[10],"in":[11,26,43,125,133],"the":[12,65,79,94,110],"task":[13],"of":[14,46,81,97],"generation":[15],"error":[16],"correction":[17],"(GER)":[18],"for":[19],"automatic":[20],"speech":[21],"recognition":[22],"(ASR)":[23],"post-processing.":[24],"However,":[25],"complex":[27],"noisy":[28,70,126],"environments,":[29],"they":[30],"still":[31],"face":[32],"challenges":[33],"such":[34],"as":[35],"poor":[36],"adaptability":[37,67],"and":[38,77,123,128],"low":[39],"information":[40,83],"utilization,":[41],"resulting":[42],"limited":[44],"effectiveness":[45],"GER.":[47],"To":[48],"address":[49],"these":[50],"issues,":[51],"this":[52],"paper":[53],"proposes":[54],"a":[55,73,85],"noise-robust":[56],"multi-modal":[57,82,98],"GER":[58,119],"framework":[59,63],"(Denoising":[60],"GER).":[61],"The":[62],"enhances":[64],"model\u2019s":[66,111],"to":[68,108],"different":[69],"scenarios":[71],"through":[72],"noise-adaptive":[74],"acoustic":[75],"encoder":[76],"optimizes":[78],"integration":[80],"via":[84],"heterogeneous":[86],"feature":[87],"compensation":[88],"dynamic":[89],"fusion":[90],"(HFCDF)":[91],"mechanism,":[92],"improving":[93],"LLM\u2019s":[95],"utilization":[96],"information.":[99],"Additionally,":[100],"reinforcement":[101],"learning":[102],"(RL)":[103],"training":[104],"strategies":[105],"are":[106],"introduced":[107],"enhance":[109],"predictive":[112],"capabilities.":[113],"Experimental":[114],"results":[115],"demonstrate":[116],"that":[117],"Denoising":[118],"significantly":[120],"improves":[121],"accuracy":[122],"robustness":[124],"environments":[127],"exhibits":[129],"good":[130],"generalization":[131],"abilities":[132],"unseen":[134],"noise":[135],"scenarios.":[136]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}