{"id":"https://openalex.org/W4408355354","doi":"https://doi.org/10.1109/icassp49660.2025.10890379","title":"Speech Enhancement Using Continuous Embeddings of Neural Audio Codec","display_name":"Speech Enhancement Using Continuous Embeddings of Neural Audio Codec","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355354","doi":"https://doi.org/10.1109/icassp49660.2025.10890379"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.16240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037624853","display_name":"Haoyang Li","orcid":"https://orcid.org/0000-0003-3024-1350"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haoyang Li","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116594555","display_name":"Tianyu Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tianyu Fan","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9987000226974487,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282193899154663},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.702093780040741},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6819052696228027},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.6799435615539551},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6446549296379089},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.47957128286361694},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33126300573349},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3176507353782654},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.2596519887447357},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.11211410164833069}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282193899154663},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.702093780040741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6819052696228027},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.6799435615539551},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6446549296379089},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.47957128286361694},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33126300573349},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3176507353782654},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2596519887447357},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.11211410164833069}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2502.16240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.16240","pdf_url":"https://arxiv.org/pdf/2502.16240","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.16240","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.16240","pdf_url":"https://arxiv.org/pdf/2502.16240","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1556611829","https://openalex.org/W2774389566","https://openalex.org/W2890964092","https://openalex.org/W2900381824","https://openalex.org/W2962843322","https://openalex.org/W2963045393","https://openalex.org/W2972436155","https://openalex.org/W3011982609","https://openalex.org/W3034302232","https://openalex.org/W3097906045","https://openalex.org/W3129077738","https://openalex.org/W3131332223","https://openalex.org/W3161480375","https://openalex.org/W3163652268","https://openalex.org/W3167533889","https://openalex.org/W3206809722","https://openalex.org/W3215615641","https://openalex.org/W4221144097","https://openalex.org/W4225905067","https://openalex.org/W4281820413","https://openalex.org/W4296069339","https://openalex.org/W4297841790","https://openalex.org/W4307323391","https://openalex.org/W4313679638","https://openalex.org/W4380551955","https://openalex.org/W4384080510","https://openalex.org/W4387323811","https://openalex.org/W4392909571","https://openalex.org/W4400111385","https://openalex.org/W4402111399","https://openalex.org/W4402111962","https://openalex.org/W4402112643","https://openalex.org/W4402115964","https://openalex.org/W4406859288","https://openalex.org/W6779577414","https://openalex.org/W6848735303","https://openalex.org/W6853515095","https://openalex.org/W6856434366","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2374470469","https://openalex.org/W2159899134","https://openalex.org/W2899318368","https://openalex.org/W2363660481","https://openalex.org/W2352448339","https://openalex.org/W2370747337","https://openalex.org/W2129913000","https://openalex.org/W137020845","https://openalex.org/W2787189739","https://openalex.org/W1542588102"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,12,120],"Neural":[3],"Audio":[4],"Codec":[5],"(NAC)":[6],"models":[7],"have":[8],"inspired":[9],"their":[10],"use":[11],"various":[13],"speech":[14,18,49],"processing":[15],"tasks,":[16],"including":[17],"enhancement":[19],"(SE).":[20],"In":[21],"this":[22],"work,":[23],"we":[24,55],"propose":[25],"a":[26,37,98,109,121,130],"novel,":[27],"efficient":[28,76,132],"SE":[29,44,57,80,91,134],"approach":[30],"by":[31],"leveraging":[32],"the":[33,59,64,72],"pre-quantization":[34],"output":[35],"of":[36,63,103,112],"pretrained":[38,65],"NAC":[39,142],"encoder.":[40],"Unlike":[41],"prior":[42],"NAC-based":[43,133],"methods,":[45],"which":[46,67],"process":[47],"discrete":[48],"tokens":[50],"using":[51],"Language":[52],"Models":[53],"(LMs),":[54],"perform":[56],"within":[58],"continuous":[60],"embedding":[61],"space":[62],"NAC,":[66],"is":[68,143],"highly":[69],"compressed":[70],"along":[71],"time":[73],"dimension":[74],"for":[75,138],"representation.":[77],"Our":[78],"lightweight":[79],"model,":[81],"optimized":[82],"through":[83],"an":[84],"embedding-level":[85],"loss,":[86],"delivers":[87],"results":[88],"comparable":[89],"to":[90,118,145],"baselines":[92],"trained":[93],"on":[94],"larger":[95],"datasets,":[96],"with":[97],"significantly":[99],"lower":[100],"real-time":[101],"factor":[102],"0.005.":[104],"Additionally,":[105],"our":[106],"method":[107],"achieves":[108],"low":[110],"GMAC":[111],"3.94,":[113],"reducing":[114],"complexity":[115],"18-fold":[116],"compared":[117],"Sepformer":[119],"simulated":[122],"cloud-based":[123],"audio":[124,147],"transmission":[125],"environment.":[126],"This":[127],"work":[128],"highlights":[129],"new,":[131],"solution,":[135],"particularly":[136],"suitable":[137],"cloud":[139],"applications":[140],"where":[141],"used":[144],"compress":[146],"before":[148],"transmission.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}