{"id":"https://openalex.org/W4414359269","doi":"https://doi.org/10.24963/ijcai.2025/912","title":"SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation","display_name":"SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359269","doi":"https://doi.org/10.24963/ijcai.2025/912"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/912","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5057012334","display_name":"Zhaoxi Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhaoxi Mu","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595335","display_name":"Xinyu Yang","orcid":"https://orcid.org/0009-0004-4716-8641"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Yang","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367292","display_name":"Gang Wang","orcid":"https://orcid.org/0000-0001-5859-3724"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Xi'an Jiaotong University"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5057012334"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13931693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8204","last_page":"8212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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":0.9941999912261963,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9387000203132629,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.52920001745224},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5160999894142151},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45910000801086426},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4562000036239624},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4271000027656555},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.3959999978542328},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3718000054359436},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.36550000309944153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567999958992004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6990000009536743},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4562000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39879998564720154},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3718000054359436},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.32899999618530273},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/912","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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":[],"abstract_inverted_index":{"While":[0],"contemporary":[1],"speech":[2,57,107,147],"separation":[3,148],"technologies":[4],"adeptly":[5],"process":[6],"lengthy":[7],"mixed":[8],"audio":[9,49],"waveforms,":[10],"they":[11],"are":[12],"frequently":[13],"challenged":[14],"by":[15],"the":[16,34,59,89,96,128,134,144],"intricacies":[17],"of":[18,91,133,146],"real-world":[19],"environments,":[20],"including":[21],"noisy":[22],"and":[23,55,76,94,122,130],"reverberant":[24],"settings,":[25],"which":[26],"can":[27],"result":[28],"in":[29,33,101,154],"artifacts":[30],"or":[31],"distortions":[32],"separated":[35],"speech.":[36],"To":[37],"overcome":[38],"these":[39],"limitations,":[40],"we":[41,87,116],"introduce":[42],"SepALM,":[43],"a":[44,70,72,74],"pioneering":[45],"approach":[46],"that":[47,104,139],"employs":[48],"language":[50,112],"models":[51,113],"(ALMs)":[52],"to":[53,126],"rectify":[54],"re-synthesize":[56],"within":[58],"text":[60],"domain":[61],"following":[62],"preliminary":[63],"separation.":[64],"SepALM":[65,140],"comprises":[66],"four":[67],"core":[68],"components:":[69],"separator,":[71],"corrector,":[73],"synthesizer,":[75],"an":[77,81],"aligner.":[78],"By":[79],"integrating":[80],"ALM-based":[82],"end-to-end":[83],"error":[84,92],"correction":[85],"mechanism,":[86],"mitigate":[88],"risk":[90],"accumulation":[93],"circumvent":[95],"optimization":[97],"hurdles":[98],"typically":[99],"encountered":[100],"conventional":[102],"methods":[103],"amalgamate":[105],"automatic":[106],"recognition":[108],"(ASR)":[109],"with":[110],"large":[111],"(LLMs).":[114],"Additionally,":[115],"have":[117],"developed":[118],"Chain-of-Thought":[119],"(CoT)":[120],"prompting":[121],"knowledge":[123],"distillation":[124],"techniques":[125],"facilitate":[127],"reasoning":[129],"training":[131],"processes":[132],"ALM.":[135],"Our":[136],"experiments":[137],"substantiate":[138],"not":[141],"only":[142],"elevates":[143],"precision":[145],"but":[149],"also":[150],"markedly":[151],"bolsters":[152],"adaptability":[153],"novel":[155],"acoustic":[156],"environments.":[157]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}