Matches in SemOpenAlex for { <https://semopenalex.org/work/W4211231901> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4211231901 abstract "In natural environments, the performance of automatic speech recognition systems is often affected by environmental noise. The noise data augmentation method is commonly used to boost acoustic models’ robustness; however, audios with background noise may degrade the acoustic model's performance in clean audios. In this paper, we propose an approach of adversarial training with gated convolutional neural networks for robust speech recognition. We use generative adversarial networks and gated convolutional neural networks to allow the acoustic model to learn noise-invariant information. Specifically, we choose the first several layers of the acoustic model as the generator model. Systematic experiments on aishell-1 show that adversarial training with gated convolutional neural networks boosts the robustness of the acoustic model in noisy environments and improves the performance of the acoustic model in quiet environments. Compared with the simple noise data augmentation training method, adversarial training with gated convolutional neural networks reduces the average relative error rate by 4.4% on the clean test data and 5.6% on the noisy test data." @default.
- W4211231901 created "2022-02-13" @default.
- W4211231901 creator A5008729293 @default.
- W4211231901 creator A5030559313 @default.
- W4211231901 creator A5085553416 @default.
- W4211231901 date "2021-11-01" @default.
- W4211231901 modified "2023-10-17" @default.
- W4211231901 title "Adversarial Training with Gated Convolutional Neural Networks for Robust Speech Recognition" @default.
- W4211231901 cites W2046932483 @default.
- W4211231901 cites W2127141656 @default.
- W4211231901 cites W2296167893 @default.
- W4211231901 cites W2395579298 @default.
- W4211231901 cites W2593414223 @default.
- W4211231901 cites W2936774411 @default.
- W4211231901 cites W2962684181 @default.
- W4211231901 cites W2962909949 @default.
- W4211231901 cites W2962959469 @default.
- W4211231901 cites W2963242190 @default.
- W4211231901 cites W2972320711 @default.
- W4211231901 cites W2981857663 @default.
- W4211231901 cites W3016010032 @default.
- W4211231901 cites W3097777922 @default.
- W4211231901 doi "https://doi.org/10.1109/cis54983.2021.00032" @default.
- W4211231901 hasPublicationYear "2021" @default.
- W4211231901 type Work @default.
- W4211231901 citedByCount "1" @default.
- W4211231901 countsByYear W42112319012023 @default.
- W4211231901 crossrefType "proceedings-article" @default.
- W4211231901 hasAuthorship W4211231901A5008729293 @default.
- W4211231901 hasAuthorship W4211231901A5030559313 @default.
- W4211231901 hasAuthorship W4211231901A5085553416 @default.
- W4211231901 hasConcept C104317684 @default.
- W4211231901 hasConcept C108583219 @default.
- W4211231901 hasConcept C115961682 @default.
- W4211231901 hasConcept C119857082 @default.
- W4211231901 hasConcept C153180895 @default.
- W4211231901 hasConcept C154945302 @default.
- W4211231901 hasConcept C155635449 @default.
- W4211231901 hasConcept C16910744 @default.
- W4211231901 hasConcept C185592680 @default.
- W4211231901 hasConcept C199360897 @default.
- W4211231901 hasConcept C28490314 @default.
- W4211231901 hasConcept C40969351 @default.
- W4211231901 hasConcept C41008148 @default.
- W4211231901 hasConcept C50644808 @default.
- W4211231901 hasConcept C55493867 @default.
- W4211231901 hasConcept C61328038 @default.
- W4211231901 hasConcept C63479239 @default.
- W4211231901 hasConcept C81363708 @default.
- W4211231901 hasConcept C99498987 @default.
- W4211231901 hasConceptScore W4211231901C104317684 @default.
- W4211231901 hasConceptScore W4211231901C108583219 @default.
- W4211231901 hasConceptScore W4211231901C115961682 @default.
- W4211231901 hasConceptScore W4211231901C119857082 @default.
- W4211231901 hasConceptScore W4211231901C153180895 @default.
- W4211231901 hasConceptScore W4211231901C154945302 @default.
- W4211231901 hasConceptScore W4211231901C155635449 @default.
- W4211231901 hasConceptScore W4211231901C16910744 @default.
- W4211231901 hasConceptScore W4211231901C185592680 @default.
- W4211231901 hasConceptScore W4211231901C199360897 @default.
- W4211231901 hasConceptScore W4211231901C28490314 @default.
- W4211231901 hasConceptScore W4211231901C40969351 @default.
- W4211231901 hasConceptScore W4211231901C41008148 @default.
- W4211231901 hasConceptScore W4211231901C50644808 @default.
- W4211231901 hasConceptScore W4211231901C55493867 @default.
- W4211231901 hasConceptScore W4211231901C61328038 @default.
- W4211231901 hasConceptScore W4211231901C63479239 @default.
- W4211231901 hasConceptScore W4211231901C81363708 @default.
- W4211231901 hasConceptScore W4211231901C99498987 @default.
- W4211231901 hasFunder F4320321001 @default.
- W4211231901 hasLocation W42112319011 @default.
- W4211231901 hasOpenAccess W4211231901 @default.
- W4211231901 hasPrimaryLocation W42112319011 @default.
- W4211231901 hasRelatedWork W2114390296 @default.
- W4211231901 hasRelatedWork W2337926734 @default.
- W4211231901 hasRelatedWork W2738221750 @default.
- W4211231901 hasRelatedWork W3156786002 @default.
- W4211231901 hasRelatedWork W4311257506 @default.
- W4211231901 hasRelatedWork W4320802194 @default.
- W4211231901 hasRelatedWork W4366224123 @default.
- W4211231901 hasRelatedWork W4381487685 @default.
- W4211231901 hasRelatedWork W4381832759 @default.
- W4211231901 hasRelatedWork W564581980 @default.
- W4211231901 isParatext "false" @default.
- W4211231901 isRetracted "false" @default.
- W4211231901 workType "article" @default.