{"id":"https://openalex.org/W4224932134","doi":"https://doi.org/10.1109/icassp43922.2022.9747454","title":"Music Enhancement via Image Translation and Vocoding","display_name":"Music Enhancement via Image Translation and Vocoding","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932134","doi":"https://doi.org/10.1109/icassp43922.2022.9747454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747454","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5056645742","display_name":"Nikhil Kandpal","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikhil Kandpal","raw_affiliation_strings":["University of North Carolina at Chapel Hill,Computer Science Department,Chapel Hill,NC,USA","Computer Science Department, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill,Computer Science Department,Chapel Hill,NC,USA","institution_ids":["https://openalex.org/I114027177"]},{"raw_affiliation_string":"Computer Science Department, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110542743","display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA","Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research,San Francisco,CA,USA","Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research,San Francisco,CA,USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3124","last_page":"3128"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.909061074256897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7559921741485596},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5847992300987244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.545552670955658},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4826003313064575},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4821998178958893},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.432958722114563},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4246240258216858},{"id":"https://openalex.org/keywords/image-translation","display_name":"Image translation","score":0.41480347514152527},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3692997694015503},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3517913222312927},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3253055810928345},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1303895115852356}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.909061074256897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559921741485596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5847992300987244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.545552670955658},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4826003313064575},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4821998178958893},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.432958722114563},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4246240258216858},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.41480347514152527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3692997694015503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3517913222312927},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3253055810928345},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1303895115852356},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"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/icassp43922.2022.9747454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747454","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2006129368","https://openalex.org/W2120847449","https://openalex.org/W2144404214","https://openalex.org/W2153894152","https://openalex.org/W2172491908","https://openalex.org/W2194775991","https://openalex.org/W2402047267","https://openalex.org/W2502312327","https://openalex.org/W2711335087","https://openalex.org/W2746457594","https://openalex.org/W2800675406","https://openalex.org/W2952218014","https://openalex.org/W2963073614","https://openalex.org/W2970006822","https://openalex.org/W2972785266","https://openalex.org/W2990594533","https://openalex.org/W3015338123","https://openalex.org/W3036167779","https://openalex.org/W3037149862","https://openalex.org/W3096159803","https://openalex.org/W3097945073","https://openalex.org/W3099330747","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3160506022","https://openalex.org/W3160652646","https://openalex.org/W3161480375","https://openalex.org/W3197042120","https://openalex.org/W3198234802","https://openalex.org/W3208743843","https://openalex.org/W4200483526","https://openalex.org/W6651792446","https://openalex.org/W6712692208","https://openalex.org/W6724804524","https://openalex.org/W6729966448","https://openalex.org/W6750948671","https://openalex.org/W6767111847","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6802609832"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W107154053"],"abstract_inverted_index":{"Consumer-grade":[0],"music":[1,33,52,70,116],"recordings":[2,34],"such":[3],"as":[4],"those":[5],"captured":[6],"by":[7,35],"mobile":[8],"devices":[9],"typically":[10],"contain":[11],"distortions":[12],"in":[13,45,93,114],"the":[14,95,104,115],"form":[15],"of":[16,106],"background":[17],"noise,":[18],"reverb,":[19],"and":[20,49,81],"microphone-induced":[21],"EQ.":[22],"This":[23],"paper":[24],"presents":[25],"a":[26,51,99],"deep":[27],"learning":[28],"approach":[29,68,84],"to":[30,60,69,89],"enhance":[31],"low-quality":[32],"combining":[36],"(i)":[37],"an":[38,82],"image-to-image":[39],"translation":[40],"model":[41,54],"for":[42,55,78],"manipulating":[43],"audio":[44,108],"its":[46],"mel-spectrogram":[47,79],"representation":[48],"(ii)":[50],"vocoding":[53],"mapping":[56,86],"synthetically":[57],"generated":[58],"mel-spectrograms":[59],"perceptually":[61],"realistic":[62],"waveforms.":[63,91],"We":[64],"find":[65],"that":[66],"this":[67],"enhancement":[71,109],"outperforms":[72],"baselines":[73],"which":[74],"use":[75],"classical":[76],"methods":[77],"inversion":[80],"end-to-end":[83],"directly":[85],"noisy":[87],"waveforms":[88],"clean":[90],"Additionally,":[92],"evaluating":[94],"proposed":[96],"method":[97],"with":[98],"listening":[100],"test,":[101],"we":[102],"analyze":[103],"reliability":[105],"common":[107],"evaluation":[110],"metrics":[111],"when":[112],"used":[113],"domain.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}