Matches in SemOpenAlex for { <https://semopenalex.org/work/W3096159803> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W3096159803 abstract "Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new speech content, and new environments. It significantly outperforms state-of-the-art baseline methods in both objective and subjective experiments." @default.
- W3096159803 created "2020-11-09" @default.
- W3096159803 creator A5027546450 @default.
- W3096159803 creator A5034842939 @default.
- W3096159803 creator A5049924184 @default.
- W3096159803 date "2020-10-25" @default.
- W3096159803 modified "2023-10-16" @default.
- W3096159803 title "HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks" @default.
- W3096159803 doi "https://doi.org/10.21437/interspeech.2020-2143" @default.
- W3096159803 hasPublicationYear "2020" @default.
- W3096159803 type Work @default.
- W3096159803 sameAs 3096159803 @default.
- W3096159803 citedByCount "56" @default.
- W3096159803 countsByYear W30961598032020 @default.
- W3096159803 countsByYear W30961598032021 @default.
- W3096159803 countsByYear W30961598032022 @default.
- W3096159803 countsByYear W30961598032023 @default.
- W3096159803 crossrefType "proceedings-article" @default.
- W3096159803 hasAuthorship W3096159803A5027546450 @default.
- W3096159803 hasAuthorship W3096159803A5034842939 @default.
- W3096159803 hasAuthorship W3096159803A5049924184 @default.
- W3096159803 hasBestOaLocation W30961598032 @default.
- W3096159803 hasConcept C113364801 @default.
- W3096159803 hasConcept C121332964 @default.
- W3096159803 hasConcept C154945302 @default.
- W3096159803 hasConcept C163294075 @default.
- W3096159803 hasConcept C24890656 @default.
- W3096159803 hasConcept C2776459999 @default.
- W3096159803 hasConcept C28490314 @default.
- W3096159803 hasConcept C37736160 @default.
- W3096159803 hasConcept C41008148 @default.
- W3096159803 hasConcept C76155785 @default.
- W3096159803 hasConceptScore W3096159803C113364801 @default.
- W3096159803 hasConceptScore W3096159803C121332964 @default.
- W3096159803 hasConceptScore W3096159803C154945302 @default.
- W3096159803 hasConceptScore W3096159803C163294075 @default.
- W3096159803 hasConceptScore W3096159803C24890656 @default.
- W3096159803 hasConceptScore W3096159803C2776459999 @default.
- W3096159803 hasConceptScore W3096159803C28490314 @default.
- W3096159803 hasConceptScore W3096159803C37736160 @default.
- W3096159803 hasConceptScore W3096159803C41008148 @default.
- W3096159803 hasConceptScore W3096159803C76155785 @default.
- W3096159803 hasLocation W30961598031 @default.
- W3096159803 hasLocation W30961598032 @default.
- W3096159803 hasOpenAccess W3096159803 @default.
- W3096159803 hasPrimaryLocation W30961598031 @default.
- W3096159803 hasRelatedWork W2468514837 @default.
- W3096159803 hasRelatedWork W2963258858 @default.
- W3096159803 hasRelatedWork W2971455341 @default.
- W3096159803 hasRelatedWork W3005226846 @default.
- W3096159803 hasRelatedWork W3208312582 @default.
- W3096159803 hasRelatedWork W4225288502 @default.
- W3096159803 hasRelatedWork W4226051017 @default.
- W3096159803 hasRelatedWork W4226067002 @default.
- W3096159803 hasRelatedWork W4288343117 @default.
- W3096159803 hasRelatedWork W4306789193 @default.
- W3096159803 isParatext "false" @default.
- W3096159803 isRetracted "false" @default.
- W3096159803 magId "3096159803" @default.
- W3096159803 workType "article" @default.