{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:16:01Z","timestamp":1764400561707,"version":"3.46.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249281","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"619-624","source":"Crossref","is-referenced-by-count":0,"title":["Analysis of Speaker Verification Performance Trade-Offs with Neural Audio Codec Transmission"],"prefix":"10.1109","author":[{"given":"Nirmalya Mallick","family":"Thakur","sequence":"first","affiliation":[{"name":"Indian Institute of Science Education and Research,Bhopal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia Qi","family":"Yip","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP48485.2024.10445746"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1002\/0470870109"},{"key":"ref3","article-title":"Soundstream: An end-to-end neural audio codec","author":"Zeghidour","year":"2021","journal-title":"arXiv"},{"key":"ref4","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023","journal-title":"arXiv"},{"key":"ref6","article-title":"Dasb - discrete audio and speech benchmark","author":"Mousavi","year":"2024","journal-title":"arXiv"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.21437\/Interspeech.2020-2650"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.21437\/Interspeech.2023-1513"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.21437\/Interspeech.2023-1294"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref11","article-title":"High-quality, low-delay music coding in the opus codec","author":"Valin","year":"2016","journal-title":"arXiv"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICASSP49660.2025.10888389"},{"volume-title":"Modelscope: Bring the notion of model-as-a-service to life","year":"2023","author":"Team","key":"ref13"},{"key":"ref14","article-title":"SpeechBrain: A general-purpose speech toolkit","author":"Ravanelli","year":"2021","journal-title":"arXiv"},{"issue":"11","key":"ref15","article-title":"Visualizing data using t-sne","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","article-title":"Optimizing neural speech codec for low-bitrate compression via multi-scale encoding","author":"Yang","year":"2024","journal-title":"arXiv"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2022","journal-title":"arXiv"},{"key":"ref19","article-title":"Neural networks fail to learn periodic functions and how to fix it","author":"Ziyin","year":"2020","journal-title":"arXiv"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.21437\/Interspeech.2024-1191"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.18653\/v1\/2024.findings-acl.616"},{"key":"ref22","article-title":"Speaker anonymization using neural audio codec language models","author":"Panariello","year":"2024","journal-title":"arXiv"},{"key":"ref23","article-title":"Representation collapsing problems in vector quantization","author":"Zhao","year":"2024","journal-title":"arXiv"},{"key":"ref24","article-title":"Discrete audio representation as an alternative to mel-spectrograms for speaker and speech recognition","author":"Puvvada","year":"2023","journal-title":"arXiv"},{"volume-title":"ITU-T, Wideband coding of speech at around 16 kbit\/s using Adaptive Multi-Rate Wideband (AMRWB), Standard, ITU-T Recommendation G.722.2","year":"2003","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.3403\/01108975u"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249281.pdf?arnumber=11249281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:11:15Z","timestamp":1764400275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249281\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249281","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}