{"id":"https://openalex.org/W4403676543","doi":"https://doi.org/10.23919/softcom62040.2024.10722025","title":"Advancing Neural Speech Codecs: Integrating Psychoacoustic Models for Enhanced Speech Quality","display_name":"Advancing Neural Speech Codecs: Integrating Psychoacoustic Models for Enhanced Speech Quality","publication_year":2024,"publication_date":"2024-09-26","ids":{"openalex":"https://openalex.org/W4403676543","doi":"https://doi.org/10.23919/softcom62040.2024.10722025"},"language":"en","primary_location":{"id":"doi:10.23919/softcom62040.2024.10722025","is_oa":false,"landing_page_url":"https://doi.org/10.23919/softcom62040.2024.10722025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)","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/A5068018386","display_name":"Adilson Torres","orcid":null},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Adilson Torres","raw_affiliation_strings":["Federal University of Lavras,Department of Computer Science,Lavras,Minas Gerais,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Lavras,Department of Computer Science,Lavras,Minas Gerais,Brazil","institution_ids":["https://openalex.org/I1315085146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054066072","display_name":"Renata Lopes Rosa","orcid":"https://orcid.org/0000-0002-7595-7187"},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Renata L. Rosa","raw_affiliation_strings":["Federal University of Lavras,Department of Computer Science,Lavras,Minas Gerais,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Lavras,Department of Computer Science,Lavras,Minas Gerais,Brazil","institution_ids":["https://openalex.org/I1315085146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063050171","display_name":"Dem\u00f3stenes Zegarra Rodr\u00edguez","orcid":"https://orcid.org/0000-0001-5401-7551"},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Dem\u00f3stenes Z. Rodr\u00edguez","raw_affiliation_strings":["Federal University of Lavras,Department of Computer Science,Lavras,Minas Gerais,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal University of Lavras,Department of Computer Science,Lavras,Minas Gerais,Brazil","institution_ids":["https://openalex.org/I1315085146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035372534","display_name":"Muhammad Saadi","orcid":"https://orcid.org/0000-0001-7901-7435"},"institutions":[{"id":"https://openalex.org/I192392021","display_name":"University of Central Punjab","ror":"https://ror.org/04g0mqe67","country_code":"PK","type":"education","lineage":["https://openalex.org/I192392021"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Saadi","raw_affiliation_strings":["University of Central Punjab,Department of Electrical Engineering,Punjab,Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Punjab,Department of Electrical Engineering,Punjab,Pakistan","institution_ids":["https://openalex.org/I192392021"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6602,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67643089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.7383999824523926,"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"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.7383999824523926,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7063999772071838,"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/psychoacoustics","display_name":"Psychoacoustics","score":0.8078998327255249},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.773762583732605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7277565002441406},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5280084609985352},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.48119741678237915},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4796341061592102},{"id":"https://openalex.org/keywords/psqm","display_name":"PSQM","score":0.439724326133728},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.17490342259407043},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1120951771736145},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10107949376106262},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.0640726089477539},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.050091713666915894}],"concepts":[{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.8078998327255249},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773762583732605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7277565002441406},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5280084609985352},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.48119741678237915},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4796341061592102},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.439724326133728},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.17490342259407043},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1120951771736145},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10107949376106262},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0640726089477539},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.050091713666915894},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/softcom62040.2024.10722025","is_oa":false,"landing_page_url":"https://doi.org/10.23919/softcom62040.2024.10722025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2918849697","https://openalex.org/W2961711175","https://openalex.org/W2998733532","https://openalex.org/W3110277971","https://openalex.org/W3133931948","https://openalex.org/W3163658555","https://openalex.org/W4224245236","https://openalex.org/W4224916783","https://openalex.org/W4224919007","https://openalex.org/W4285044837","https://openalex.org/W4323896987","https://openalex.org/W4324360595","https://openalex.org/W4364360650","https://openalex.org/W4372267315","https://openalex.org/W4375869173","https://openalex.org/W4377699820"],"related_works":["https://openalex.org/W2129913000","https://openalex.org/W2069597661","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W2541680182"],"abstract_inverted_index":{"Voice":[0],"quality":[1,144,155,181],"is":[2,94,120],"a":[3,68,77,82,130],"vital":[4],"component":[5],"of":[6,13,56,67,89,114,133,160,170],"mobile":[7],"communication":[8],"systems,":[9],"and":[10,58,81,91,110,126,163,195],"the":[11,20,46,53,65,72,98,112,115,142,150,158,168,174],"advent":[12],"neural":[14,49,164],"speech":[15,21,50,102,165,198],"codecs":[16,51],"has":[17],"significantly":[18],"transformed":[19],"compression":[22,59],"landscape.":[23],"Traditional":[24],"codecs,":[25,166],"with":[26,60,71],"their":[27],"reliance":[28],"on":[29],"fixed":[30],"signal":[31],"processing":[32],"pipelines,":[33],"often":[34],"falter":[35],"at":[36,183],"lower":[37,184],"bit":[38],"rates,":[39],"leading":[40],"to":[41,96,108,140,177],"decreased":[42],"voice":[43,134,154,180],"quality.":[44,135],"On":[45],"other":[47,138],"hand,":[48],"provide":[52],"dual":[54],"benefits":[55],"enhancement":[57,200],"negligible":[61],"latency.":[62],"We":[63],"propose":[64],"integration":[66,159],"psychoacoustic":[69,161],"model":[70,162,172],"existing":[73],"structure":[74],"that":[75],"comprises":[76],"convolutional":[78],"encoder,":[79],"decoder,":[80],"residual":[83],"vector":[84],"quantizer.":[85],"A":[86],"unique":[87],"combination":[88],"reconstruction":[90,143],"adversarial":[92],"loss":[93],"employed":[95],"train":[97],"model,":[99],"targeting":[100],"high-quality":[101],"content":[103],"generation.":[104],"Simulations":[105],"are":[106,145],"conducted":[107],"study":[109],"optimize":[111],"performance":[113],"proposed":[116],"model.":[117],"Performance":[118],"assessment":[119],"carry":[121],"out":[122],"using":[123],"MUSHRA":[124],"measures":[125],"POLQA":[127],"scores,":[128],"offering":[129],"comprehensive":[131],"understanding":[132],"In":[136],"addition,":[137],"models":[139],"compare":[141],"utilized.":[146],"Our":[147],"results":[148],"highlight":[149],"substantial":[151],"improvements":[152],"in":[153,197],"enabled":[156],"by":[157],"demonstrating":[167],"superiority":[169],"our":[171],"over":[173],"conventional":[175],"approach":[176],"deliver":[178],"superior":[179],"services":[182],"bitrates.":[185],"It":[186],"also":[187],"provides":[188],"an":[189],"enriched":[190],"basis":[191],"for":[192],"future":[193],"research":[194],"development":[196],"codec":[199],"strategies.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}