{"id":"https://openalex.org/W4372260101","doi":"https://doi.org/10.1109/icassp49357.2023.10096056","title":"High Quality Audio Coding with Mdctnet","display_name":"High Quality Audio Coding with Mdctnet","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260101","doi":"https://doi.org/10.1109/icassp49357.2023.10096056"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096056","doi":"https://doi.org/10.1109/icassp49357.2023.10096056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096056","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2212.04583","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049163770","display_name":"Grant A. Davidson","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grant Davidson","raw_affiliation_strings":["Dolby Laboratories, Inc.,San Francisco,CA,USA,94103"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Inc.,San Francisco,CA,USA,94103","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028754831","display_name":"Mark S. Vinton","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Vinton","raw_affiliation_strings":["Dolby Laboratories, Inc.,San Francisco,CA,USA,94103"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Inc.,San Francisco,CA,USA,94103","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076963590","display_name":"Per Ekstrand","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Per Ekstrand","raw_affiliation_strings":["Dolby Sweden AB,Stockholm,Sweden,113 30"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Sweden AB,Stockholm,Sweden,113 30","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102733043","display_name":"Cong Zhou","orcid":"https://orcid.org/0000-0002-4379-0298","observed_orcids":["https://orcid.org/0000-0002-4379-0298"]},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Zhou","raw_affiliation_strings":["Dolby Laboratories, Inc.,San Francisco,CA,USA,94103"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Inc.,San Francisco,CA,USA,94103","institution_ids":["https://openalex.org/I4210093996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030554103","display_name":"Lars F. Villemoes","orcid":"https://orcid.org/0009-0006-3011-5476","observed_orcids":["https://orcid.org/0009-0006-3011-5476"]},"institutions":[{"id":"https://openalex.org/I4210093833","display_name":"Dolby (Sweden)","ror":"https://ror.org/00gqs6306","country_code":"SE","type":"company","lineage":["https://openalex.org/I4210093833","https://openalex.org/I4210093996"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Lars Villemoes","raw_affiliation_strings":["Dolby Sweden AB,Stockholm,Sweden,113 30"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Sweden AB,Stockholm,Sweden,113 30","institution_ids":["https://openalex.org/I4210093833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":"https://orcid.org/0009-0001-1856-8556","observed_orcids":["https://orcid.org/0009-0001-1856-8556","https://orcid.org/0009-0006-2790-7587"]},"institutions":[{"id":"https://openalex.org/I4210093996","display_name":"Dolby (United States)","ror":"https://ror.org/01eyenr26","country_code":"US","type":"company","lineage":["https://openalex.org/I4210093996"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Dolby Laboratories, Inc.,San Francisco,CA,USA,94103"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dolby Laboratories, Inc.,San Francisco,CA,USA,94103","institution_ids":["https://openalex.org/I4210093996"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6666,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94155751,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"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":0.7778000235557556,"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":0.7778000235557556,"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":0.17419999837875366,"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":0.027699999511241913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-compression","display_name":"audio compression","score":0.6850000023841858},{"id":"https://openalex.org/keywords/modified-discrete-cosine-transform","display_name":"modified discrete cosine transform","score":0.9409999847412109},{"id":"https://openalex.org/keywords/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.9120000004768372},{"id":"https://openalex.org/keywords/subjective-listening-tests","display_name":"subjective listening tests","score":0.6129999756813049},{"id":"https://openalex.org/keywords/monophonic-audio","display_name":"monophonic audio","score":0.7860000133514404}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7741197943687439},{"id":"https://openalex.org/C57667952","wikidata":"https://www.wikidata.org/wiki/Q1154443","display_name":"Variable bitrate","level":3,"score":0.7555077075958252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428170442581177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.647789478302002},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.6097093820571899},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6051978468894958},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5863097906112671},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4866076707839966},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4834800362586975},{"id":"https://openalex.org/C34339180","wikidata":"https://www.wikidata.org/wiki/Q1325924","display_name":"Constant bitrate","level":4,"score":0.4365561306476593},{"id":"https://openalex.org/C98526533","wikidata":"https://www.wikidata.org/wiki/Q1691938","display_name":"Sub-band coding","level":3,"score":0.43216192722320557},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.4313713312149048},{"id":"https://openalex.org/C28726691","wikidata":"https://www.wikidata.org/wiki/Q1268231","display_name":"Modified discrete cosine transform","level":5,"score":0.410871684551239},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32620811462402344},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.3021392822265625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13611698150634766},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.12914487719535828},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09311577677726746},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096056","doi":"https://doi.org/10.1109/icassp49357.2023.10096056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096056","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2212.04583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.04583","pdf_url":"https://arxiv.org/pdf/2212.04583","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2212.04583","doi":"https://doi.org/10.48550/arxiv.2212.04583","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.04583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2212.04583","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.04583","pdf_url":"https://arxiv.org/pdf/2212.04583","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372260101.pdf","grobid_xml":"https://content.openalex.org/works/W4372260101.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1504652801","https://openalex.org/W1522301498","https://openalex.org/W1885680957","https://openalex.org/W2100351681","https://openalex.org/W2148431558","https://openalex.org/W2772926198","https://openalex.org/W2775336875","https://openalex.org/W2896030002","https://openalex.org/W2899725768","https://openalex.org/W2924551963","https://openalex.org/W2936557804","https://openalex.org/W2944209089","https://openalex.org/W2948211236","https://openalex.org/W3015567712","https://openalex.org/W3015780049","https://openalex.org/W3016003977","https://openalex.org/W3110277971","https://openalex.org/W3130248090","https://openalex.org/W3169882120","https://openalex.org/W3178321840","https://openalex.org/W4224919007","https://openalex.org/W4285186333","https://openalex.org/W4375928773","https://openalex.org/W6630448252"],"related_works":["https://openalex.org/W4403511251","https://openalex.org/W4406461725","https://openalex.org/W4375869436","https://openalex.org/W4404101961","https://openalex.org/W6903767905","https://openalex.org/W4377699820","https://openalex.org/W7161676242","https://openalex.org/W4372267191","https://openalex.org/W4372270198","https://openalex.org/W7220748106"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,49,63,68],"neural":[3],"audio":[4,40,55,65],"generative":[5],"model,":[6],"MDCTNet,":[7],"operating":[8],"in":[9,29],"the":[10,25,87,91,108],"perceptually":[11],"weighted":[12],"domain":[13],"of":[14,24,52,90,104],"an":[15],"adaptive":[16],"modified":[17],"discrete":[18],"cosine":[19],"transform":[20],"(MDCT).":[21],"The":[22],"architecture":[23],"model":[26],"captures":[27],"correlations":[28],"both":[30,85],"time":[31],"and":[32],"frequency":[33],"directions":[34],"with":[35,72],"recurrent":[36],"layers":[37],"(RNNs).":[38],"An":[39],"coding":[41],"system":[42,93],"is":[43,100],"obtained":[44],"by":[45,62],"training":[46],"MDCTNet":[47],"on":[48],"diverse":[50],"set":[51],"fullband":[53],"monophonic":[54],"signals":[56],"at":[57,106],"48":[58],"kHz":[59],"sampling,":[60],"conditioned":[61],"perceptual":[64],"encoder.":[66],"In":[67],"subjective":[69],"listening":[70],"test":[71],"ten":[73],"excerpts":[74],"chosen":[75],"to":[76,102],"be":[77],"balanced":[78],"across":[79],"content":[80],"types,":[81],"yet":[82],"critical":[83],"for":[84,94],"codecs,":[86],"mean":[88],"performance":[89],"proposed":[92],"24":[95],"kb/s":[96],"variable":[97],"bitrate":[98],"(VBR)":[99],"similar":[101],"that":[103],"Opus":[105],"twice":[107],"bitrate.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2023-05-07T00:00:00"}
