{"id":"https://openalex.org/W4415536280","doi":"https://doi.org/10.1145/3746027.3754988","title":"From Continuous to Discrete: Cross-Domain Collaborative General Speech Enhancement via Hierarchical Language Models","display_name":"From Continuous to Discrete: Cross-Domain Collaborative General Speech Enhancement via Hierarchical Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415536280","doi":"https://doi.org/10.1145/3746027.3754988"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0004-7393-0425","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073675630","display_name":"Rilin Chen","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":"Rilin Chen","raw_affiliation_strings":["Tencent AI Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6873-1683","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053757616","display_name":"Andong Li","orcid":"https://orcid.org/0000-0003-4094-8448"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andong Li","raw_affiliation_strings":["Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4094-8448","affiliations":[{"raw_affiliation_string":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0031-9156","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056067943","display_name":"Xinyu Yang","orcid":"https://orcid.org/0000-0001-5117-4914"},"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, Xi'an, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-5117-4914","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0520-6844","affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.36917012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"219","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9868000149726868,"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/codebook","display_name":"Codebook","score":0.796999990940094},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.746999979019165},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6642000079154968},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5468000173568726},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46059998869895935},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4007999897003174},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3977000117301941},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.39570000767707825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7990999817848206},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.796999990940094},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.746999979019165},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5468000173568726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4007999897003174},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28519999980926514},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25609999895095825},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754988","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754988","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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":7,"referenced_works":["https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205689591","https://openalex.org/W4385756463","https://openalex.org/W4388979610","https://openalex.org/W4406417959","https://openalex.org/W4412945293"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"OmniGSE,":[3],"a":[4,45,78,95,117,124],"novel":[5],"general":[6,132],"speech":[7,18,110,178],"enhancement":[8,179],"(GSE)":[9],"framework":[10],"designed":[11,116],"to":[12,52,107],"mitigate":[13],"the":[14,55,70,87,100,139,143,171],"diverse":[15],"distortions":[16,25,60],"that":[17,81,153],"signals":[19],"encounter":[20],"in":[21,61,163,180],"real-world":[22,181],"scenarios.":[23,63],"These":[24,168],"include":[26],"background":[27],"noise,":[28],"reverberation,":[29],"bandwidth":[30],"limitations,":[31],"signal":[32],"clipping,":[33],"and":[34,74,126,176],"network":[35],"packet":[36],"loss.":[37],"Existing":[38],"methods":[39],"typically":[40],"focus":[41],"on":[42],"optimizing":[43],"for":[44,174],"single":[46],"type":[47],"of":[48,58,72,123],"distortion,":[49],"often":[50],"struggling":[51],"effectively":[53],"handle":[54],"simultaneous":[56],"presence":[57],"multiple":[59,127,159],"complex":[62],"OmniGSE":[64,154],"bridges":[65],"this":[66],"gap":[67],"by":[68],"integrating":[69],"strengths":[71],"discriminative":[73],"generative":[75],"approaches":[76],"through":[77,111],"two-stage":[79],"architecture":[80],"enables":[82],"cross-domain":[83],"collaborative":[84],"optimization.":[85],"In":[86,99],"first":[88],"stage,":[89,102],"continuous":[90],"features":[91,134],"are":[92,105],"enhanced":[93],"using":[94],"lightweight":[96],"channel-split":[97],"NAC-RoFormer.":[98],"second":[101],"discrete":[103],"tokens":[104],"generated":[106],"reconstruct":[108],"high-quality":[109],"language":[112,119],"models.":[113],"Specifically,":[114],"we":[115],"hierarchical":[118],"model":[120],"structure":[121],"consisting":[122],"RootLM":[125,130],"BranchLMs.":[128],"The":[129],"models":[131,157],"acoustic":[133],"across":[135,158],"codebook":[136,148],"layers,":[137],"while":[138],"BranchLMs":[140],"explicitly":[141],"capture":[142],"progressive":[144],"relationships":[145],"between":[146],"different":[147],"levels.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"surpasses":[155],"existing":[156],"benchmarks,":[160],"particularly":[161],"excelling":[162],"scenarios":[164],"involving":[165],"compound":[166],"distortions.":[167],"findings":[169],"underscore":[170],"framework's":[172],"potential":[173],"robust":[175],"versatile":[177],"applications.":[182]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-25T00:00:00"}