{"id":"https://openalex.org/W3186609711","doi":"https://doi.org/10.1109/waspaa52581.2021.9632723","title":"Harp-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding","display_name":"Harp-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3186609711","doi":"https://doi.org/10.1109/waspaa52581.2021.9632723","mag":"3186609711"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"preprint","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/A5018337836","display_name":"Darius Petermann","orcid":"https://orcid.org/0000-0002-5973-5752"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Darius Petermann","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071537541","display_name":"Seungkwon Beack","orcid":"https://orcid.org/0000-0002-6254-2062"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungkwon Beack","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064582903","display_name":"Minje Kim","orcid":"https://orcid.org/0000-0003-3513-8328"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Minje Kim","raw_affiliation_strings":["Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018337836"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":1.4569,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.8415896,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"316","last_page":"320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.9076601266860962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.789870023727417},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7626561522483826},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.622176468372345},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6037716865539551},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5936559438705444},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4174407720565796},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.41279736161231995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4018709659576416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36506158113479614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35099363327026367},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.31261569261550903},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2032347023487091}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9076601266860962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789870023727417},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7626561522483826},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.622176468372345},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6037716865539551},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5936559438705444},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4174407720565796},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.41279736161231995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4018709659576416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36506158113479614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35099363327026367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31261569261550903},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2032347023487091},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632723","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":29,"referenced_works":["https://openalex.org/W1885680957","https://openalex.org/W1901129140","https://openalex.org/W2100495367","https://openalex.org/W2105921478","https://openalex.org/W2165291881","https://openalex.org/W2476548250","https://openalex.org/W2519091744","https://openalex.org/W2732044853","https://openalex.org/W2774707525","https://openalex.org/W2775336875","https://openalex.org/W2924551963","https://openalex.org/W2935711438","https://openalex.org/W2949382160","https://openalex.org/W2963091184","https://openalex.org/W2963182577","https://openalex.org/W2963452667","https://openalex.org/W2964164354","https://openalex.org/W2972354707","https://openalex.org/W2972519044","https://openalex.org/W3015268401","https://openalex.org/W3110277971","https://openalex.org/W4205788663","https://openalex.org/W6639363673","https://openalex.org/W6639824700","https://openalex.org/W6741057705","https://openalex.org/W6746914816","https://openalex.org/W6751512325","https://openalex.org/W6764117752","https://openalex.org/W6773743766"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2145836866","https://openalex.org/W2803255133"],"abstract_inverted_index":{"We":[0,94,125],"propose":[1],"a":[2,30,63,67,111],"novel":[3],"autoencoder":[4,65,141],"architecture":[5,132],"that":[6,32,114,128],"improves":[7,133],"the":[8,37,52,71,87,92,102,116,121,129],"architectural":[9],"scalability":[10],"of":[11,55,75,98,104,108],"general-purpose":[12],"neural":[13],"audio":[14,135],"coding":[15],"models.":[16],"An":[17],"autoencoder-based":[18],"codec":[19,113],"employs":[20],"quantization":[21],"to":[22,138],"turn":[23],"its":[24,76],"bottleneck":[25],"layer":[26,69,90],"activation":[27],"into":[28],"bitstrings,":[29],"process":[31],"hinders":[33],"information":[34,83],"flow":[35],"between":[36,51,120],"encoder":[38,78,89],"and":[39],"decoder":[40,68],"parts.":[41],"To":[42],"circumvent":[43],"this":[44,96],"issue,":[45],"we":[46],"employ":[47],"additional":[48,82,105],"skip":[49,99],"connections":[50,100],"corresponding":[53,77,88],"pair":[54],"encoder-decoder":[56,123],"layers.":[57,124],"The":[58],"assumption":[59],"is":[60,110],"that,":[61],"in":[62,101],"mirrored":[64],"topology,":[66],"reconstructs":[70],"intermediate":[72],"feature":[73],"representation":[74],"layer.":[79],"Hence,":[80],"any":[81],"directly":[84],"propagated":[85],"from":[86],"helps":[91],"reconstruction.":[93],"implement":[95],"kind":[97],"form":[103],"autoencoders,":[106],"each":[107],"which":[109],"small":[112],"compresses":[115],"massive":[117],"data":[118],"transfer":[119],"paired":[122],"empirically":[126],"verify":[127],"proposed":[130],"hyper-autoencoded":[131],"perceptual":[134],"quality":[136],"compared":[137],"an":[139],"ordinary":[140],"baseline.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}