{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T17:58:43Z","timestamp":1772301523382,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T00:00:00Z","timestamp":1697932800000},"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":[[2023,10,22]]},"DOI":"10.1109\/waspaa58266.2023.10248144","type":"proceedings-article","created":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T17:31:37Z","timestamp":1694799097000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Martin","family":"Strauss","sequence":"first","affiliation":[{"name":"International Audio Laboratories Erlangen,Erlangen,Germany,91058"}]},{"given":"Nicola","family":"Pia","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS,Erlangen,Germany"}]},{"given":"Nagashree K. S.","family":"Rao","sequence":"additional","affiliation":[{"name":"Fraunhofer IIS,Erlangen,Germany"}]},{"given":"Bernd","family":"Edler","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen,Erlangen,Germany,91058"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Denoising Diffusion Implicit Models","author":"song","year":"2021","journal-title":"9th Int Conf on Learning Representations ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10653"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11829"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref11","article-title":"Universal Speech Enhancement with Score-based Diffusion","author":"serr\u00e0","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-517"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3198548"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-302"},{"key":"ref17","article-title":"Improved Speech Enhancement with the Wave-U-Net","author":"macartney","year":"2018"},{"key":"ref16","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref18","first-page":"17 022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume":"33","author":"kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref23","first-page":"626","article-title":"SDR – Half-baked or Well Done?","author":"roux","year":"2019","journal-title":"Proc IEEE Intl Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref26","article-title":"Recommendation ITU–T P.862 Perceptual evaluation of speech quality (PESQ), and objective method for end-to-end speech quality assessment of narrowband telephone band and wideband digital codes","year":"2000"},{"key":"ref25","article-title":"SpeechBrain: A General-Purpose Speech Toolkit","author":"ravanelli","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref21","article-title":"CSR-I (WSJ0) Complete","author":"garofolo","year":"0"},{"key":"ref28","article-title":"Recommendation ITU–R BS.1534-3 Method for the subjective assessment of intermediate quality level of audio systems","year":"2015"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022898"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref3","article-title":"Dialog+ in Broadcasting: First Field Tests using Deep-Learning Based Dialogue Enhancement","author":"matteo","year":"2021","journal-title":"Int Broadcast Conv (IBC) Technical Papers"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413999"}],"event":{"name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"New Paltz, NY, USA","start":{"date-parts":[[2023,10,22]]},"end":{"date-parts":[[2023,10,25]]}},"container-title":["2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10248019\/10248047\/10248144.pdf?arnumber=10248144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T17:41:07Z","timestamp":1696268467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10248144\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,22]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/waspaa58266.2023.10248144","relation":{},"subject":[],"published":{"date-parts":[[2023,10,22]]}}}