{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:26Z","timestamp":1774419986781,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890357","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["On the Relation Between Speech Quality and Quantized Latent Representations of Neural Codecs"],"prefix":"10.1109","author":[{"given":"Mhd Modar","family":"Halimeh","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Torcoli","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philipp","family":"Grundhuber","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanu\u00ebl A. P.","family":"Habets","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Integrated Circuits IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069302"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref7","article-title":"Evaluation of quality for audio encoding at low bit rates","volume-title":"Audio Eng. Soc. (AES) Conv. 82","author":"Brandenburg"},{"key":"ref8","article-title":"Method for objective measurement of perceived audio quality","year":"2023","journal-title":"Int. Telecommunication Union (ITU) Rec. BS.1387-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref10","article-title":"HiFi++:: a unified framework for neural vocoding, bandwidth extension and speech enhancement","author":"Andreev","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683277"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447523"},{"key":"ref17","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"ref18","first-page":"3327","article-title":"Direct speech-to-speech translation with discrete units","volume-title":"Annual Meeting of the Association for Computational Linguistics","author":"Lee"},{"key":"ref19","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref20","article-title":"Self-supervised speech quality estimation and enhancement using only clean speech","volume-title":"The Twelfth International Conference on Learning Representations","author":"Fu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1191"},{"key":"ref22","article-title":"SCOREQ: Speech quality assessment with contrastive regression","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Ragano"},{"key":"ref23","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"The Thirty-fourth Conference on Neural Information Processing Systems","author":"Baevski"},{"key":"ref24","article-title":"Neural discrete representation learning","volume-title":"the International Conference on Neural Information Processing Systems","author":"van den Oord"},{"key":"ref25","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2017","journal-title":"University of Edinburgh, The Centre for Speech Technology Research (CSTR)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447634"},{"key":"ref28","article-title":"Recommendation ITU-R BS.1534-3: Method for the subjective assessment of intermediate quality level of audio systems","year":"2015","journal-title":"Int. Telecommunication Union (ITU), Radiocommunication Sector"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2024.101685"},{"key":"ref30","article-title":"Recommendation ITU-T P.835: Subjective test methodology for evaluating speech communication systems that include noise suppression algorithm","year":"2003","journal-title":"Int. Telecommunication Union (ITU), Telecommuniocation Standardization Sector"},{"key":"ref31","first-page":"76","article-title":"ETSI TS 103 281 v1.3.1: Speech and Multimedia Transmission Quality (STQ); Speech Quality in the Presence of Background Noise: Objective Test Methods for Super-Wideband and Fullband Terminals","year":"2019"},{"key":"ref32","article-title":"An Examination and Interpretation of ITU-R BS.1387: Perceptual Evaluation of Audio Quality","author":"Kabal","year":"2002","journal-title":"MMSP Lab Technical Report, McGill University, Tech. Rep."}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890357.pdf?arnumber=10890357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:47Z","timestamp":1774416347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890357\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890357","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}