{"id":"https://openalex.org/W4416798764","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249281","title":"Analysis of Speaker Verification Performance Trade-Offs with Neural Audio Codec Transmission","display_name":"Analysis of Speaker Verification Performance Trade-Offs with Neural Audio Codec Transmission","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798764","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249281"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5089135944","display_name":"Nirmalya Thakur","orcid":"https://orcid.org/0000-0002-3225-1870"},"institutions":[{"id":"https://openalex.org/I288749910","display_name":"Indian Institute of Science Education and Research, Bhopal","ror":"https://ror.org/02rb21j89","country_code":"IN","type":"education","lineage":["https://openalex.org/I288749910"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nirmalya Mallick Thakur","raw_affiliation_strings":["Indian Institute of Science Education and Research,Bhopal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Education and Research,Bhopal","institution_ids":["https://openalex.org/I288749910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941083","display_name":"Jia Qi Yip","orcid":"https://orcid.org/0000-0002-9896-9658"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jia Qi Yip","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17633777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"619","last_page":"624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9128999710083008,"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":0.9128999710083008,"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/T10860","display_name":"Speech and Audio Processing","score":0.04699999839067459,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.006399999838322401,"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/codec","display_name":"Codec","score":0.8102999925613403},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4092000126838684},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.387800008058548},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3662000000476837},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.36570000648498535},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.36469998955726624}],"concepts":[{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.8102999925613403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7766000032424927},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6499999761581421},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3662000000476837},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.36570000648498535},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.34279999136924744},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":11,"referenced_works":["https://openalex.org/W2726515241","https://openalex.org/W3024869864","https://openalex.org/W3180355996","https://openalex.org/W4238850318","https://openalex.org/W4243239301","https://openalex.org/W4385822954","https://openalex.org/W4385823321","https://openalex.org/W4392910569","https://openalex.org/W4402111541","https://openalex.org/W4402670057","https://openalex.org/W4408352172"],"related_works":[],"abstract_inverted_index":{"Neural":[0],"audio":[1,18,25,43],"codecs":[2,44,71],"(NACs)":[3],"have":[4],"made":[5],"significant":[6],"advancements":[7],"in":[8,16,64],"recent":[9],"years":[10],"and":[11,41,70,102,190],"are":[12,162],"rapidly":[13],"being":[14],"adopted":[15],"many":[17],"processing":[19],"pipelines.":[20],"However,":[21],"they":[22],"can":[23,142],"introduce":[24],"distortions":[26],"which":[27,141,150],"degrade":[28],"speaker":[29],"verification":[30],"(SV)":[31],"performance.":[32],"This":[33],"study":[34],"investigates":[35],"the":[36,55,133,175],"impact":[37],"of":[38,118,136],"both":[39],"traditional":[40,86,167],"neural":[42],"at":[45,96,106,126,177],"varying":[46],"bitrates":[47,73,108,128],"on":[48,54,184],"three":[49],"state-of-the-art":[50],"SV":[51,65,81,192],"models":[52,69],"evaluated":[53],"VoxCeleb1":[56],"dataset.":[57],"Our":[58,157],"findings":[59],"reveal":[60],"a":[61,163],"consistent":[62],"degradation":[63],"performance":[66,82],"across":[67],"all":[68],"as":[72],"decrease.":[74],"Notably,":[75],"NACs":[76,137,161,187],"do":[77],"not":[78],"fundamentally":[79],"break":[80],"when":[83],"compared":[84],"to":[85,132,153,166],"codecs.":[87],"They":[88],"outperform":[89],"Opus":[90,149],"by":[91],"<tex":[92,120],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[93,99,110,121],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{6-8":[94],"\\%}$</tex>":[95],"low-bitrates":[97],"(<tex":[98,109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$&lt;12":[100],"\\text{kbps}$</tex>)":[101],"remain":[103],"marginally":[104],"behind":[105],"higher":[107,127,178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\approx":[111],"24":[112],"\\text{kbps}$</tex>),":[113],"with":[114],"an":[115],"EER":[116],"increase":[117],"only":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$0.4-0.7":[122],"\\%$</tex>.":[123],"The":[124],"disparity":[125],"is":[129],"likely":[130],"due":[131],"primary":[134],"optimization":[135],"for":[138],"perceptual":[139],"quality,":[140],"inadvertently":[143],"discard":[144],"critical":[145],"speaker-discriminative":[146],"features,":[147],"unlike":[148],"was":[151],"designed":[152],"preserve":[154],"vocal":[155],"characteristics.":[156],"investigation":[158],"suggests":[159],"that":[160],"feasible":[164],"alternative":[165],"codecs,":[168],"especially":[169],"under":[170],"bandwidth":[171],"limitations.":[172],"To":[173],"bridge":[174],"gap":[176],"bitrates,":[179],"future":[180],"work":[181],"should":[182],"focus":[183],"developing":[185],"speaker-aware":[186],"or":[188],"retraining":[189],"adapting":[191],"models.":[193]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}