Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295122182> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W4295122182 abstract "Deep neural network (DNN)-based speech enhancement ordinarily requires clean speech signals as the training target. However, collecting clean signals is very costly because they must be recorded in a studio. This requirement currently restricts the amount of training data for speech enhancement to less than 1/1000 of that of speech recognition which does not need clean signals. Increasing the amount of training data is important for improving the performance, and hence the requirement of clean signals should be relaxed. In this paper, we propose a training strategy that does not require clean signals. The proposed method only utilizes noisy signals for training, which enables us to use a variety of speech signals in the wild. Our experimental results showed that the proposed method can achieve the performance similar to that of a DNN trained with clean signals." @default.
- W4295122182 created "2022-09-10" @default.
- W4295122182 creator A5015534419 @default.
- W4295122182 creator A5034837951 @default.
- W4295122182 creator A5048172594 @default.
- W4295122182 creator A5075732053 @default.
- W4295122182 date "2021-01-21" @default.
- W4295122182 modified "2023-09-25" @default.
- W4295122182 title "Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech" @default.
- W4295122182 doi "https://doi.org/10.48550/arxiv.2101.08625" @default.
- W4295122182 hasPublicationYear "2021" @default.
- W4295122182 type Work @default.
- W4295122182 citedByCount "0" @default.
- W4295122182 crossrefType "posted-content" @default.
- W4295122182 hasAuthorship W4295122182A5015534419 @default.
- W4295122182 hasAuthorship W4295122182A5034837951 @default.
- W4295122182 hasAuthorship W4295122182A5048172594 @default.
- W4295122182 hasAuthorship W4295122182A5075732053 @default.
- W4295122182 hasBestOaLocation W42951221821 @default.
- W4295122182 hasConcept C121332964 @default.
- W4295122182 hasConcept C153294291 @default.
- W4295122182 hasConcept C154945302 @default.
- W4295122182 hasConcept C163294075 @default.
- W4295122182 hasConcept C204201278 @default.
- W4295122182 hasConcept C2776182073 @default.
- W4295122182 hasConcept C2777211547 @default.
- W4295122182 hasConcept C28490314 @default.
- W4295122182 hasConcept C2984842247 @default.
- W4295122182 hasConcept C41008148 @default.
- W4295122182 hasConcept C50644808 @default.
- W4295122182 hasConcept C51632099 @default.
- W4295122182 hasConcept C61328038 @default.
- W4295122182 hasConceptScore W4295122182C121332964 @default.
- W4295122182 hasConceptScore W4295122182C153294291 @default.
- W4295122182 hasConceptScore W4295122182C154945302 @default.
- W4295122182 hasConceptScore W4295122182C163294075 @default.
- W4295122182 hasConceptScore W4295122182C204201278 @default.
- W4295122182 hasConceptScore W4295122182C2776182073 @default.
- W4295122182 hasConceptScore W4295122182C2777211547 @default.
- W4295122182 hasConceptScore W4295122182C28490314 @default.
- W4295122182 hasConceptScore W4295122182C2984842247 @default.
- W4295122182 hasConceptScore W4295122182C41008148 @default.
- W4295122182 hasConceptScore W4295122182C50644808 @default.
- W4295122182 hasConceptScore W4295122182C51632099 @default.
- W4295122182 hasConceptScore W4295122182C61328038 @default.
- W4295122182 hasLocation W42951221821 @default.
- W4295122182 hasOpenAccess W4295122182 @default.
- W4295122182 hasPrimaryLocation W42951221821 @default.
- W4295122182 hasRelatedWork W1576113739 @default.
- W4295122182 hasRelatedWork W2394461504 @default.
- W4295122182 hasRelatedWork W2764005420 @default.
- W4295122182 hasRelatedWork W3000194274 @default.
- W4295122182 hasRelatedWork W3015358918 @default.
- W4295122182 hasRelatedWork W3115527998 @default.
- W4295122182 hasRelatedWork W3135356379 @default.
- W4295122182 hasRelatedWork W4210341744 @default.
- W4295122182 hasRelatedWork W4312095890 @default.
- W4295122182 hasRelatedWork W4320085895 @default.
- W4295122182 isParatext "false" @default.
- W4295122182 isRetracted "false" @default.
- W4295122182 workType "article" @default.