{"id":"https://openalex.org/W4408345865","doi":"https://doi.org/10.1109/icassp49660.2025.10890357","title":"On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs","display_name":"On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345865","doi":"https://doi.org/10.1109/icassp49660.2025.10890357"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5008815790","display_name":"Mhd Modar Halimeh","orcid":"https://orcid.org/0000-0001-6113-3067"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mhd Modar Halimeh","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021417399","display_name":"Matteo Torcoli","orcid":"https://orcid.org/0000-0003-2834-9194"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Matteo Torcoli","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116591583","display_name":"Philipp Grundhuber","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Grundhuber","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany","institution_ids":["https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0245835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9702000021934509,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9702000021934509,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9513999819755554,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9251000285148621,"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/computer-science","display_name":"Computer science","score":0.7612012624740601},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.719068169593811},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6227741241455078},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6045758724212646},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5374135971069336},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4622281491756439},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45487651228904724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4246489405632019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38461801409721375},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3588024973869324},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11326545476913452},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10048609972000122}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7612012624740601},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.719068169593811},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6227741241455078},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6045758724212646},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5374135971069336},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4622281491756439},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45487651228904724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4246489405632019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38461801409721375},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3588024973869324},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11326545476913452},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10048609972000122},{"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":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890357","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/489986","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/489986","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2127851351","https://openalex.org/W2144404214","https://openalex.org/W2516001803","https://openalex.org/W2752796333","https://openalex.org/W2935711438","https://openalex.org/W2963091184","https://openalex.org/W2972359262","https://openalex.org/W2998733532","https://openalex.org/W3097934054","https://openalex.org/W3145029257","https://openalex.org/W3161480375","https://openalex.org/W3215615641","https://openalex.org/W4307323391","https://openalex.org/W4372270198","https://openalex.org/W4391421598","https://openalex.org/W4392903389","https://openalex.org/W4392904585","https://openalex.org/W6632870766","https://openalex.org/W6780218876","https://openalex.org/W6798080464","https://openalex.org/W6809863597","https://openalex.org/W6849105126","https://openalex.org/W6861531434","https://openalex.org/W6873606913","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W2129913000","https://openalex.org/W2374470469","https://openalex.org/W1911859126","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W2899318368","https://openalex.org/W3095556352","https://openalex.org/W2159899134","https://openalex.org/W2363660481","https://openalex.org/W2120730869"],"abstract_inverted_index":{"Neural":[0],"audio":[1],"signal":[2,51,83],"codecs":[3],"have":[4],"attracted":[5],"significant":[6],"attention":[7],"in":[8],"recent":[9],"years.":[10],"In":[11,37],"essence,":[12],"the":[13,30,42,45,49,58,75,78,92,114,125],"impressive":[14],"low":[15],"bitrate":[16],"achieved":[17],"by":[18,23,53],"such":[19],"encoders":[20],"is":[21,155],"enabled":[22],"learning":[24],"an":[25],"abstract":[26],"representation":[27,47],"that":[28,113,153],"captures":[29],"properties":[31],"of":[32,48,60,128],"encoded":[33],"signals,":[34],"e.g.,":[35],"speech.":[36,129],"this":[38,135],"work,":[39],"we":[40,66],"investigate":[41],"relation":[43],"between":[44],"latent":[46],"input":[50],"learned":[52],"a":[54,86,132,137,156],"neural":[55,80],"codec":[56],"and":[57,147],"quality":[59,108,127,163],"speech":[61,82,88,107,162],"signals.":[62],"To":[63],"do":[64],"so,":[65],"introduce":[67],"Latent-representation-to-Quantization":[68],"error":[69],"Ratio":[70],"(LQR)":[71],"measures,":[72],"which":[73],"quantify":[74],"distance":[76],"from":[77],"idealized":[79],"codec\u2019s":[81],"model":[84],"for":[85,159],"given":[87],"signal.":[89],"We":[90],"compare":[91],"proposed":[93,115],"metrics":[94],"to":[95,120],"intrusive":[96,148],"measures":[97],"as":[98,100],"well":[99],"data-driven":[101],"supervised":[102],"methods":[103],"using":[104],"two":[105],"subjective":[106,126],"datasets.":[109],"This":[110],"analysis":[111],"shows":[112],"LQR":[116,154],"correlates":[117],"strongly":[118],"(up":[119],"0.9":[121],"Pearson\u2019s":[122],"correlation)":[123],"with":[124],"Despite":[130],"being":[131],"non-intrusive":[133],"metric,":[134],"yields":[136],"competitive":[138],"performance":[139],"with,":[140],"or":[141],"even":[142],"better":[143],"than,":[144],"other":[145],"pre-trained":[146],"measures.":[149,164],"These":[150],"results":[151],"show":[152],"promising":[157],"basis":[158],"more":[160],"sophisticated":[161]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}