{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:06:21Z","timestamp":1730297181023,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"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":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10022898","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"444-450","source":"Crossref","is-referenced-by-count":4,"title":["Improved Normalizing Flow-Based Speech Enhancement Using an all-Pole Gammatone Filterbank for Conditional Input Representation"],"prefix":"10.1109","author":[{"given":"Martin","family":"Strauss","sequence":"first","affiliation":[{"name":"Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matteo","family":"Torcoli","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernd","family":"Edler","sequence":"additional","affiliation":[{"name":"Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Fraunhofer IIS,International Audio Laboratories,Erlangen,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687942"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/89.966083"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860851"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5743773"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632794"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632770"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053164"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-1672"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"volume-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":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref19","article-title":"Unrolled Generative Adversarial Networks","volume-title":"5th Int. Conf. on Learning Representations, ICLR","author":"Metz","year":"2017"},{"key":"ref20","article-title":"Denoising Diffusion Implicit Models","volume-title":"9th Int. Conf. on Learning Representations, ICLR","author":"Song","year":"2021"},{"issue":"57","key":"ref21","first-page":"1","article-title":"Normalizing Flows for Probabilistic Modeling and Inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","article-title":"Density Estimation Using Real NVP","volume-title":"5th Int. Conf. on Learning Representations, ICLR","author":"Dinh","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2979603"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413999"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413605"},{"key":"ref27","first-page":"205","article-title":"All-pole models of auditory filtering","author":"Lyon","year":"1997","journal-title":"Diversity in Auditory Mechanics"},{"key":"ref28","first-page":"10215","article-title":"Glow: Generative Flow with Invertible 1x1 Convolutions","volume-title":"Advances in Neural Information Processing Systems 31","author":"Kingma","year":"2018"},{"article-title":"Analyzing Inverse Problems with Invertible Neural Networks","volume-title":"7th Int. Conf. on Learning Representations, ICLR, 2019","author":"Ardizzone","key":"ref29"},{"journal-title":"WaveNet: A Generative Model for Raw Audio","year":"2016","author":"van den Oord","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-159"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2013.6709856"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1121\/1.4799597"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"journal-title":"SpeechBrain: A General-Purpose Speech Toolkit","year":"2021","author":"Ravanelli","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.911054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069302"},{"volume-title":"Recommendation ITU\u2013R BS.1534-3 Method for the subjective assessment of intermediate quality level of audio systems","year":"2015","key":"ref39"},{"volume-title":"Recommendation ITU\u2013R BS.1770-4 Algorithms to measure audio programme loudness and true-peak audio level","year":"2015","key":"ref40"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1418"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5334\/jors.187"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2023,1,9]]},"location":"Doha, Qatar","end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10022898.pdf?arnumber=10022898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:36:27Z","timestamp":1707806187000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10022898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10022898","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}