Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287777752> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4287777752 abstract "The INTERSPEECH 2020 Deep Noise Suppression (DNS) Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. While the performance is good on the synthetic test set, often the model performance degrades significantly on real recordings. Also, most of the conventional objective metrics do not correlate well with subjective tests and lab subjective tests are not scalable for a large test set. In this challenge, we open-sourced a large clean speech and noise corpus for training the noise suppression models and a representative test set to real-world scenarios consisting of both synthetic and real recordings. We also open-sourced an online subjective test framework based on ITU-T P.808 for researchers to reliably test their developments. We evaluated the results using P.808 on a blind test set. The results and the key learnings from the challenge are discussed. The datasets and scripts can be found here for quick access https://github.com/microsoft/DNS-Challenge." @default.
- W4287777752 created "2022-07-26" @default.
- W4287777752 creator A5001022750 @default.
- W4287777752 creator A5007693985 @default.
- W4287777752 creator A5012734251 @default.
- W4287777752 creator A5015176399 @default.
- W4287777752 creator A5016472660 @default.
- W4287777752 creator A5023537206 @default.
- W4287777752 creator A5024067566 @default.
- W4287777752 creator A5033592362 @default.
- W4287777752 creator A5033701513 @default.
- W4287777752 creator A5042412445 @default.
- W4287777752 creator A5049524680 @default.
- W4287777752 creator A5068040769 @default.
- W4287777752 creator A5086512263 @default.
- W4287777752 date "2020-05-16" @default.
- W4287777752 modified "2023-10-17" @default.
- W4287777752 title "The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results" @default.
- W4287777752 doi "https://doi.org/10.48550/arxiv.2005.13981" @default.
- W4287777752 hasPublicationYear "2020" @default.
- W4287777752 type Work @default.
- W4287777752 citedByCount "0" @default.
- W4287777752 crossrefType "posted-content" @default.
- W4287777752 hasAuthorship W4287777752A5001022750 @default.
- W4287777752 hasAuthorship W4287777752A5007693985 @default.
- W4287777752 hasAuthorship W4287777752A5012734251 @default.
- W4287777752 hasAuthorship W4287777752A5015176399 @default.
- W4287777752 hasAuthorship W4287777752A5016472660 @default.
- W4287777752 hasAuthorship W4287777752A5023537206 @default.
- W4287777752 hasAuthorship W4287777752A5024067566 @default.
- W4287777752 hasAuthorship W4287777752A5033592362 @default.
- W4287777752 hasAuthorship W4287777752A5033701513 @default.
- W4287777752 hasAuthorship W4287777752A5042412445 @default.
- W4287777752 hasAuthorship W4287777752A5049524680 @default.
- W4287777752 hasAuthorship W4287777752A5068040769 @default.
- W4287777752 hasAuthorship W4287777752A5086512263 @default.
- W4287777752 hasBestOaLocation W42877777521 @default.
- W4287777752 hasConcept C111919701 @default.
- W4287777752 hasConcept C115961682 @default.
- W4287777752 hasConcept C119857082 @default.
- W4287777752 hasConcept C124101348 @default.
- W4287777752 hasConcept C151730666 @default.
- W4287777752 hasConcept C154945302 @default.
- W4287777752 hasConcept C169903167 @default.
- W4287777752 hasConcept C177264268 @default.
- W4287777752 hasConcept C199360897 @default.
- W4287777752 hasConcept C2777267654 @default.
- W4287777752 hasConcept C28490314 @default.
- W4287777752 hasConcept C41008148 @default.
- W4287777752 hasConcept C48044578 @default.
- W4287777752 hasConcept C51632099 @default.
- W4287777752 hasConcept C61423126 @default.
- W4287777752 hasConcept C77088390 @default.
- W4287777752 hasConcept C86803240 @default.
- W4287777752 hasConcept C99498987 @default.
- W4287777752 hasConceptScore W4287777752C111919701 @default.
- W4287777752 hasConceptScore W4287777752C115961682 @default.
- W4287777752 hasConceptScore W4287777752C119857082 @default.
- W4287777752 hasConceptScore W4287777752C124101348 @default.
- W4287777752 hasConceptScore W4287777752C151730666 @default.
- W4287777752 hasConceptScore W4287777752C154945302 @default.
- W4287777752 hasConceptScore W4287777752C169903167 @default.
- W4287777752 hasConceptScore W4287777752C177264268 @default.
- W4287777752 hasConceptScore W4287777752C199360897 @default.
- W4287777752 hasConceptScore W4287777752C2777267654 @default.
- W4287777752 hasConceptScore W4287777752C28490314 @default.
- W4287777752 hasConceptScore W4287777752C41008148 @default.
- W4287777752 hasConceptScore W4287777752C48044578 @default.
- W4287777752 hasConceptScore W4287777752C51632099 @default.
- W4287777752 hasConceptScore W4287777752C61423126 @default.
- W4287777752 hasConceptScore W4287777752C77088390 @default.
- W4287777752 hasConceptScore W4287777752C86803240 @default.
- W4287777752 hasConceptScore W4287777752C99498987 @default.
- W4287777752 hasLocation W42877777521 @default.
- W4287777752 hasOpenAccess W4287777752 @default.
- W4287777752 hasPrimaryLocation W42877777521 @default.
- W4287777752 hasRelatedWork W2113904186 @default.
- W4287777752 hasRelatedWork W2792951589 @default.
- W4287777752 hasRelatedWork W2890029653 @default.
- W4287777752 hasRelatedWork W3090337104 @default.
- W4287777752 hasRelatedWork W3099765033 @default.
- W4287777752 hasRelatedWork W3107607767 @default.
- W4287777752 hasRelatedWork W3197848046 @default.
- W4287777752 hasRelatedWork W3201070945 @default.
- W4287777752 hasRelatedWork W4225124612 @default.
- W4287777752 hasRelatedWork W4280583453 @default.
- W4287777752 isParatext "false" @default.
- W4287777752 isRetracted "false" @default.
- W4287777752 workType "article" @default.