{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:18:46Z","timestamp":1763191126503,"version":"3.45.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230926","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension"],"prefix":"10.1109","author":[{"given":"Kishan","family":"Gupta","sequence":"first","affiliation":[{"name":"Fraunhofer IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srikanth","family":"Korse","sequence":"additional","affiliation":[{"name":"International Audio Laboratories,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Brendel","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicola","family":"Pia","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillaume","family":"Fuchs","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"1999","key":"ref1","article-title":"TS 26.090, Mandatory Speech Codec speech processing functions; Adaptive Multi-Rate (AMR) speech codec; Transcoding functions"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179063"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.804299"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179109"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462529"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632750"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1255"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746296"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-430"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref11","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"article-title":"High-Fidelity Audio Compression with Improved RVQGAN","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Kumar","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447523"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3491575"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3417347"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888771"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1490"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446439"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413575"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053769"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3519881"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55844.2023.10285965"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10290072"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10290032"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287465"},{"article-title":"A lightweight and robust method for blind wideband-to-fullband extension of speech","year":"2024","author":"B\u00fcthe","key":"ref29"},{"key":"ref30","article-title":"Voice Coding with Opus","author":"Vos","year":"2013","journal-title":"Journal of The Audio Engineering Society"},{"issue":"10254","key":"ref31","article-title":"Deep Neural Network Based Guided Speech Bandwidth Extension","author":"Konstantin","year":"2019","journal-title":"Journal of the Audio Engineering Society"},{"article-title":"Finite Scalar Quantization: VQ-VAE Made Simple","volume-title":"The Twelfth Int. Conf. on Learning Representations (ICLR)","author":"Mentzer","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747733"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1609"},{"article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit","year":"2019","author":"Yamagishi","key":"ref36"},{"journal-title":"ITU-T (Telecommunication Standardization Sector), Recommendation P.501, Jan. 2017, recommendation ITU-T P.501 (01\/2017)","key":"ref37","article-title":"Test Signals for Use in Telephonometry"},{"journal-title":"European Telecommunications Standards Institute (ETSI), Technical Specification TS 103 281","article-title":"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":"ref38"},{"key":"ref39","article-title":"Super Wideband Stereo Speech Database"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref41","first-page":"1","article-title":"ViSQOL: The Virtual Speech Quality Objective Listener","volume-title":"IWAENC 2012; International Workshop on Acoustic Signal Enhancement","author":"Hines"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2665"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2366"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230926.pdf?arnumber=11230926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:16:36Z","timestamp":1763190996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230926\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230926","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}