Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225323908> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4225323908 abstract "This work focuses on online dereverberation for hearing devices using the weighted prediction error (WPE) algorithm. WPE filtering requires an estimate of the target speech power spectral density (PSD). Recently deep neural networks (DNNs) have been used for this task. However, these approaches optimize the PSD estimate which only indirectly affects the WPE output, thus potentially resulting in limited dereverberation. In this paper, we propose an end-to-end approach specialized for online processing, that directly optimizes the dereverberated output signal. In addition, we propose to adapt it to the needs of different types of hearing-device users by modifying the optimization target as well as the WPE algorithm characteristics used in training. We show that the proposed end-to-end approach outperforms the traditional and conventional DNN-supported WPEs on a noise-free version of the WHAMR! dataset." @default.
- W4225323908 created "2022-05-05" @default.
- W4225323908 creator A5006784595 @default.
- W4225323908 creator A5025828759 @default.
- W4225323908 creator A5058912393 @default.
- W4225323908 creator A5087022569 @default.
- W4225323908 date "2022-05-23" @default.
- W4225323908 modified "2023-09-26" @default.
- W4225323908 title "Customizable End-To-End Optimization Of Online Neural Network-Supported Dereverberation For Hearing Devices" @default.
- W4225323908 cites W160333422 @default.
- W4225323908 cites W1603978816 @default.
- W4225323908 cites W1997109056 @default.
- W4225323908 cites W2014768838 @default.
- W4225323908 cites W2040782121 @default.
- W4225323908 cites W2080145918 @default.
- W4225323908 cites W2096819401 @default.
- W4225323908 cites W2127851351 @default.
- W4225323908 cites W2168610508 @default.
- W4225323908 cites W2516001803 @default.
- W4225323908 cites W2530782473 @default.
- W4225323908 cites W2748661748 @default.
- W4225323908 cites W2767071179 @default.
- W4225323908 cites W2800675406 @default.
- W4225323908 cites W2899625056 @default.
- W4225323908 cites W2939777271 @default.
- W4225323908 cites W2990078986 @default.
- W4225323908 cites W3008762051 @default.
- W4225323908 cites W3015191643 @default.
- W4225323908 cites W3124056356 @default.
- W4225323908 cites W3162315798 @default.
- W4225323908 cites W4231225162 @default.
- W4225323908 doi "https://doi.org/10.1109/icassp43922.2022.9746235" @default.
- W4225323908 hasPublicationYear "2022" @default.
- W4225323908 type Work @default.
- W4225323908 citedByCount "2" @default.
- W4225323908 countsByYear W42253239082023 @default.
- W4225323908 crossrefType "proceedings-article" @default.
- W4225323908 hasAuthorship W4225323908A5006784595 @default.
- W4225323908 hasAuthorship W4225323908A5025828759 @default.
- W4225323908 hasAuthorship W4225323908A5058912393 @default.
- W4225323908 hasAuthorship W4225323908A5087022569 @default.
- W4225323908 hasBestOaLocation W42253239082 @default.
- W4225323908 hasConcept C115961682 @default.
- W4225323908 hasConcept C121332964 @default.
- W4225323908 hasConcept C127413603 @default.
- W4225323908 hasConcept C154945302 @default.
- W4225323908 hasConcept C163294075 @default.
- W4225323908 hasConcept C199360897 @default.
- W4225323908 hasConcept C201995342 @default.
- W4225323908 hasConcept C24890656 @default.
- W4225323908 hasConcept C2776182073 @default.
- W4225323908 hasConcept C2779843651 @default.
- W4225323908 hasConcept C2780451532 @default.
- W4225323908 hasConcept C2780801066 @default.
- W4225323908 hasConcept C28490314 @default.
- W4225323908 hasConcept C2984842247 @default.
- W4225323908 hasConcept C41008148 @default.
- W4225323908 hasConcept C50644808 @default.
- W4225323908 hasConcept C74296488 @default.
- W4225323908 hasConcept C99498987 @default.
- W4225323908 hasConceptScore W4225323908C115961682 @default.
- W4225323908 hasConceptScore W4225323908C121332964 @default.
- W4225323908 hasConceptScore W4225323908C127413603 @default.
- W4225323908 hasConceptScore W4225323908C154945302 @default.
- W4225323908 hasConceptScore W4225323908C163294075 @default.
- W4225323908 hasConceptScore W4225323908C199360897 @default.
- W4225323908 hasConceptScore W4225323908C201995342 @default.
- W4225323908 hasConceptScore W4225323908C24890656 @default.
- W4225323908 hasConceptScore W4225323908C2776182073 @default.
- W4225323908 hasConceptScore W4225323908C2779843651 @default.
- W4225323908 hasConceptScore W4225323908C2780451532 @default.
- W4225323908 hasConceptScore W4225323908C2780801066 @default.
- W4225323908 hasConceptScore W4225323908C28490314 @default.
- W4225323908 hasConceptScore W4225323908C2984842247 @default.
- W4225323908 hasConceptScore W4225323908C41008148 @default.
- W4225323908 hasConceptScore W4225323908C50644808 @default.
- W4225323908 hasConceptScore W4225323908C74296488 @default.
- W4225323908 hasConceptScore W4225323908C99498987 @default.
- W4225323908 hasLocation W42253239081 @default.
- W4225323908 hasLocation W42253239082 @default.
- W4225323908 hasOpenAccess W4225323908 @default.
- W4225323908 hasPrimaryLocation W42253239081 @default.
- W4225323908 hasRelatedWork W1573346329 @default.
- W4225323908 hasRelatedWork W1598166535 @default.
- W4225323908 hasRelatedWork W1620835410 @default.
- W4225323908 hasRelatedWork W2404314657 @default.
- W4225323908 hasRelatedWork W2771275309 @default.
- W4225323908 hasRelatedWork W2884250895 @default.
- W4225323908 hasRelatedWork W3115290769 @default.
- W4225323908 hasRelatedWork W4225323908 @default.
- W4225323908 hasRelatedWork W4312120858 @default.
- W4225323908 hasRelatedWork W4223638116 @default.
- W4225323908 isParatext "false" @default.
- W4225323908 isRetracted "false" @default.
- W4225323908 workType "article" @default.