{"id":"https://openalex.org/W3015780049","doi":"https://doi.org/10.1109/icassp40776.2020.9053113","title":"Audio Codec Enhancement with Generative Adversarial Networks","display_name":"Audio Codec Enhancement with Generative Adversarial Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015780049","doi":"https://doi.org/10.1109/icassp40776.2020.9053113","mag":"3015780049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5102628979","display_name":"Arijit Biswas","orcid":"https://orcid.org/0009-0009-3347-058X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Arijit Biswas","raw_affiliation_strings":["Dolby Germany GmbH, N\u00fcrnberg, Germany"],"affiliations":[{"raw_affiliation_string":"Dolby Germany GmbH, N\u00fcrnberg, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101451693","display_name":"Dai Jia","orcid":"https://orcid.org/0000-0001-5216-9025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai Jia","raw_affiliation_strings":["Dolby Laboratories, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102628979"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6565,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.93776993,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"356","last_page":"360"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.995199978351593,"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":0.8091381788253784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7832504510879517},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.7241052389144897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6642895936965942},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.6150819659233093},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6049617528915405},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.49959611892700195},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.47780662775039673},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4228770136833191},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41465047001838684},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3070860505104065},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.21445563435554504},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1688821017742157}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8091381788253784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7832504510879517},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.7241052389144897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6642895936965942},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.6150819659233093},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6049617528915405},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.49959611892700195},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.47780662775039673},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4228770136833191},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41465047001838684},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3070860505104065},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.21445563435554504},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1688821017742157},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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":36,"referenced_works":["https://openalex.org/W1963699091","https://openalex.org/W2079985975","https://openalex.org/W2094721231","https://openalex.org/W2099471712","https://openalex.org/W2117366609","https://openalex.org/W2140593795","https://openalex.org/W2395539742","https://openalex.org/W2514828952","https://openalex.org/W2519091744","https://openalex.org/W2520164769","https://openalex.org/W2593414223","https://openalex.org/W2623662528","https://openalex.org/W2647567423","https://openalex.org/W2752819676","https://openalex.org/W2769892507","https://openalex.org/W2774016059","https://openalex.org/W2775336875","https://openalex.org/W2803112028","https://openalex.org/W2809824582","https://openalex.org/W2889428811","https://openalex.org/W2893749619","https://openalex.org/W2896030002","https://openalex.org/W2944209089","https://openalex.org/W2949382160","https://openalex.org/W2952716587","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2964046669","https://openalex.org/W3096468295","https://openalex.org/W4320013936","https://openalex.org/W6726381175","https://openalex.org/W6744051579","https://openalex.org/W6751642695","https://openalex.org/W6755312952","https://openalex.org/W6755446875","https://openalex.org/W6762390287"],"related_works":["https://openalex.org/W2172523511","https://openalex.org/W2127580606","https://openalex.org/W1999835922","https://openalex.org/W2151333624","https://openalex.org/W1911859126","https://openalex.org/W1745769461","https://openalex.org/W2141927546","https://openalex.org/W2097502558","https://openalex.org/W2137616928","https://openalex.org/W2123400578"],"abstract_inverted_index":{"Audio":[0],"codecs":[1],"are":[2],"typically":[3],"transform-domain":[4],"based":[5,45],"and":[6,17,118],"efficiently":[7],"code":[8,121],"stationary":[9],"audio":[10,41,59,70,97],"signals,":[11],"but":[12],"they":[13],"struggle":[14],"with":[15,27],"speech":[16,117],"signals":[18,32],"containing":[19],"dense":[20],"transient":[21],"events":[22],"such":[23],"as":[24,33],"applause.":[25],"Specifically,":[26],"these":[28],"two":[29],"classes":[30],"of":[31,54,93,116],"examples,":[34],"we":[35],"demonstrate":[36],"a":[37],"technique":[38],"for":[39],"restoring":[40],"from":[42],"coding":[43],"noise":[44],"on":[46,68],"generative":[47],"adversarial":[48],"networks":[49],"(GAN).":[50],"A":[51],"primary":[52],"advantage":[53],"the":[55,63,73,81,90,102,110,114],"proposed":[56,111],"GAN-based":[57],"coded":[58,96],"enhancer":[60,112],"is":[61],"that":[62,109],"method":[64],"operates":[65],"end-to-end":[66],"directly":[67],"decoded":[69],"samples,":[71],"eliminating":[72],"need":[74],"to":[75,101,120],"design":[76],"any":[77,99],"manually-crafted":[78],"frontend.":[79],"Furthermore,":[80],"enhancement":[82],"approach":[83],"described":[84],"in":[85],"this":[86],"paper":[87],"can":[88],"improve":[89],"sound":[91],"quality":[92,115],"low-bit":[94],"rate":[95],"without":[98],"modifications":[100],"existent":[103],"standard-compliant":[104],"encoders.":[105],"Subjective":[106],"tests":[107],"illustrate":[108],"improves":[113],"difficult":[119],"applause":[122],"excerpts":[123],"significantly.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}