{"id":"https://openalex.org/W4408354268","doi":"https://doi.org/10.1109/icassp49660.2025.10890252","title":"High-Fidelity Music Vocoder using Neural Audio Codecs","display_name":"High-Fidelity Music Vocoder using Neural Audio Codecs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354268","doi":"https://doi.org/10.1109/icassp49660.2025.10890252"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890252","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":"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/A5092247142","display_name":"Luca A. Lanzend\u00f6rfer","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luca A. Lanzend\u00f6rfer","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023201175","display_name":"Florian Gr\u00f6tschla","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Florian Gr\u00f6tschla","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116335776","display_name":"Michael Ungersb\u00f6ck","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael Ungersb\u00f6ck","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078339613","display_name":"Roger Wattenhofer","orcid":"https://orcid.org/0000-0002-6339-3134"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roger Wattenhofer","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90607791,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"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":0.9894000291824341,"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":0.9894000291824341,"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/T11309","display_name":"Music and Audio Processing","score":0.9639000296592712,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9398999810218811,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.784881055355072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7708293795585632},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.7312516570091248},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6767407059669495},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5105105638504028},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45429766178131104},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.44843265414237976},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.277197003364563},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16838806867599487},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11772772669792175}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.784881055355072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708293795585632},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.7312516570091248},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6767407059669495},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5105105638504028},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45429766178131104},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.44843265414237976},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.277197003364563},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16838806867599487},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11772772669792175},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890252","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"}],"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/W1552314771","https://openalex.org/W2120847449","https://openalex.org/W2593116425","https://openalex.org/W2593414223","https://openalex.org/W2791686384","https://openalex.org/W2963609956","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3037038648","https://openalex.org/W3160506022","https://openalex.org/W3197273793","https://openalex.org/W3215615641","https://openalex.org/W6687506355","https://openalex.org/W6763945542","https://openalex.org/W6767111847","https://openalex.org/W6773772901","https://openalex.org/W6779577414","https://openalex.org/W6783867762","https://openalex.org/W6843673214","https://openalex.org/W6849109464","https://openalex.org/W6853515095"],"related_works":["https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W4313443006","https://openalex.org/W2543961871","https://openalex.org/W2352448339","https://openalex.org/W2945374968","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W4293777179","https://openalex.org/W4385452045"],"abstract_inverted_index":{"While":[0],"neural":[1,26,38],"vocoders":[2],"have":[3],"made":[4],"significant":[5],"progress":[6],"in":[7,86,94,105],"high-fidelity":[8,43],"speech":[9,106],"synthesis,":[10,107],"their":[11],"application":[12],"on":[13,89],"polyphonic":[14],"music":[15,87],"has":[16],"remained":[17],"underexplored.":[18],"In":[19],"this":[20],"work,":[21],"we":[22],"propose":[23],"DisCoder,":[24],"a":[25,30,37,58,78,95,112],"vocoder":[27],"that":[28],"leverages":[29],"generative":[31],"adversarial":[32],"encoder-decoder":[33],"architecture":[34],"informed":[35],"by":[36],"audio":[39,46,75],"codec":[40],"to":[41,73],"reconstruct":[42],"44.1":[44],"kHz":[45],"from":[47],"mel":[48,55],"spectrograms.":[49],"Our":[50,99],"approach":[51,100],"first":[52],"transforms":[53],"the":[54,63],"spectrogram":[56],"into":[57],"lower-dimensional":[59],"representation":[60],"aligned":[61],"with":[62],"Descript":[64],"Audio":[65],"Codec":[66],"(DAC)":[67],"latent":[68],"space":[69],"before":[70],"reconstructing":[71],"it":[72],"an":[74],"signal":[76],"using":[77],"fine-tuned":[79],"DAC":[80],"decoder.":[81],"DisCoder":[82],"achieves":[83],"state-of-the-art":[84],"performance":[85,104],"synthesis":[88],"several":[90],"objective":[91],"metrics":[92],"and":[93],"MUSHRA":[96],"listening":[97],"study.":[98],"also":[101],"shows":[102],"competitive":[103],"highlighting":[108],"its":[109],"potential":[110],"as":[111],"universal":[113],"vocoder.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}