{"id":"https://openalex.org/W4416771683","doi":"https://doi.org/10.1109/sped67700.2025.11251799","title":"ADNAC: Audio Denoiser using Neural Audio Codec","display_name":"ADNAC: Audio Denoiser using Neural Audio Codec","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416771683","doi":"https://doi.org/10.1109/sped67700.2025.11251799"},"language":null,"primary_location":{"id":"doi:10.1109/sped67700.2025.11251799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11251799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5120569524","display_name":"Daniel Jimon","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Daniel Jimon","raw_affiliation_strings":["Technical University of Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108274843","display_name":"Mircea-F. Vaida","orcid":null},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea Vaida","raw_affiliation_strings":["Technical University of Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Technical University of Cluj-Napoca,Romania"],"affiliations":[{"raw_affiliation_string":"Technical University of Cluj-Napoca,Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120569524"],"corresponding_institution_ids":["https://openalex.org/I158333966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47625046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.49390000104904175,"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":0.49390000104904175,"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":0.11270000040531158,"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":0.10740000009536743,"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/codec","display_name":"Codec","score":0.7365000247955322},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.7027999758720398},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5558000206947327},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.44749999046325684},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.43389999866485596},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.38519999384880066},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090000152587891},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7365000247955322},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.7027999758720398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6622999906539917},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5558000206947327},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.43389999866485596},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C167940747","wikidata":"https://www.wikidata.org/wiki/Q63727227","display_name":"Audio signal flow","level":5,"score":0.3409000039100647},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2976999878883362},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped67700.2025.11251799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped67700.2025.11251799","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1897240248","https://openalex.org/W2038484192","https://openalex.org/W2067295501","https://openalex.org/W2405774341","https://openalex.org/W2414102402","https://openalex.org/W2901243971","https://openalex.org/W4205689591","https://openalex.org/W4224209922","https://openalex.org/W4405974256"],"related_works":[],"abstract_inverted_index":{"Audio":[0,31],"denoising":[1],"is":[2,61],"critical":[3],"in":[4],"signal":[5],"processing,":[6],"enhancing":[7],"intelligibility":[8],"and":[9,72],"fidelity":[10,74],"for":[11,22,34,84],"applications":[12],"like":[13,45],"restoring":[14],"musical":[15],"recordings.":[16],"This":[17,37],"paper":[18,78],"presents":[19],"a":[20,24,52,64,82],"proof-of-concept":[21],"adapting":[23],"state-of-the-art":[25],"neural":[26],"audio":[27,87],"codec,":[28],"the":[29,40,49],"Descript":[30],"Codec":[32],"(DAC),":[33],"music":[35],"denoising.":[36],"work":[38],"overcomes":[39],"limitations":[41],"of":[42],"traditional":[43],"architectures":[44],"UNets":[46],"by":[47,63],"training":[48],"model":[50],"on":[51],"large-scale,":[53],"custom-synthesized":[54],"dataset":[55],"built":[56],"from":[57],"diverse":[58],"sources.":[59],"Training":[60],"guided":[62],"multi-objective":[65],"loss":[66],"function":[67],"that":[68],"combines":[69],"time-domain,":[70],"spectral,":[71],"signal-level":[73],"metrics.":[75],"Ultimately,":[76],"this":[77],"aims":[79],"to":[80],"present":[81],"PoC":[83],"high-fidelity,":[85],"generative":[86],"restoration.":[88]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-27T00:00:00"}