FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100968126> ?p ?o ?g. }

• W3100968126 abstract "In this paper we address the problem of enhancing speech signals in noisy mixtures using a source separation approach. We explore the use of neural networks as an alternative to a popular speech variance model based on supervised non-negative matrix factorization (NMF). More precisely, we use a variational autoencoder as a speaker-independent supervised generative speech model, highlighting the conceptual similarities that this approach shares with its NMF-based counterpart. In order to be free of generalization issues regarding the noisy recording environments, we follow the approach of having a supervised model only for the target speech signal, the noise model being based on unsupervised NMF. We develop a Monte Carlo expectation-maximization algorithm for inferring the latent variables in the variational autoencoder and estimating the unsupervised model parameters. Experiments show that the proposed method outperforms a semi-supervised NMF baseline and a state-of-the-art fully supervised deep learning approach." @default.
• W3100968126 created "2020-11-23" @default.
• W3100968126 creator A5020392160 @default.
• W3100968126 creator A5045593473 @default.
• W3100968126 creator A5078307335 @default.
• W3100968126 date "2018-09-01" @default.
• W3100968126 modified "2023-10-01" @default.
• W3100968126 title "A VARIANCE MODELING FRAMEWORK BASED ON VARIATIONAL AUTOENCODERS FOR SPEECH ENHANCEMENT" @default.
• W3100968126 cites W1504438288 @default.
• W3100968126 cites W1529883046 @default.
• W3100968126 cites W1552314771 @default.
• W3100968126 cites W1975593377 @default.
• W3100968126 cites W2003335470 @default.
• W3100968126 cites W2039844283 @default.
• W3100968126 cites W2044893557 @default.
• W3100968126 cites W2049633694 @default.
• W3100968126 cites W2053742104 @default.
• W3100968126 cites W2114508388 @default.
• W3100968126 cites W2127851351 @default.
• W3100968126 cites W2149273154 @default.
• W3100968126 cites W2149414429 @default.
• W3100968126 cites W2408744528 @default.
• W3100968126 cites W2519994964 @default.
• W3100968126 cites W2766672686 @default.
• W3100968126 cites W4232282348 @default.
• W3100968126 cites W4245883374 @default.
• W3100968126 cites W4245919820 @default.
• W3100968126 doi "https://doi.org/10.1109/mlsp.2018.8516711" @default.
• W3100968126 hasPublicationYear "2018" @default.
• W3100968126 type Work @default.
• W3100968126 sameAs 3100968126 @default.
• W3100968126 citedByCount "43" @default.
• W3100968126 countsByYear W31009681262019 @default.
• W3100968126 countsByYear W31009681262020 @default.
• W3100968126 countsByYear W31009681262021 @default.
• W3100968126 countsByYear W31009681262022 @default.
• W3100968126 countsByYear W31009681262023 @default.
• W3100968126 crossrefType "proceedings-article" @default.
• W3100968126 hasAuthorship W3100968126A5020392160 @default.
• W3100968126 hasAuthorship W3100968126A5045593473 @default.
• W3100968126 hasAuthorship W3100968126A5078307335 @default.
• W3100968126 hasBestOaLocation W31009681262 @default.
• W3100968126 hasConcept C101738243 @default.
• W3100968126 hasConcept C115961682 @default.
• W3100968126 hasConcept C119857082 @default.
• W3100968126 hasConcept C121332964 @default.
• W3100968126 hasConcept C134306372 @default.
• W3100968126 hasConcept C152671427 @default.
• W3100968126 hasConcept C153180895 @default.
• W3100968126 hasConcept C154945302 @default.
• W3100968126 hasConcept C158693339 @default.
• W3100968126 hasConcept C163294075 @default.
• W3100968126 hasConcept C167966045 @default.
• W3100968126 hasConcept C177148314 @default.
• W3100968126 hasConcept C2776182073 @default.
• W3100968126 hasConcept C28490314 @default.
• W3100968126 hasConcept C33923547 @default.
• W3100968126 hasConcept C39890363 @default.
• W3100968126 hasConcept C41008148 @default.
• W3100968126 hasConcept C42355184 @default.
• W3100968126 hasConcept C50644808 @default.
• W3100968126 hasConcept C62520636 @default.
• W3100968126 hasConcept C8038995 @default.
• W3100968126 hasConcept C99498987 @default.
• W3100968126 hasConceptScore W3100968126C101738243 @default.
• W3100968126 hasConceptScore W3100968126C115961682 @default.
• W3100968126 hasConceptScore W3100968126C119857082 @default.
• W3100968126 hasConceptScore W3100968126C121332964 @default.
• W3100968126 hasConceptScore W3100968126C134306372 @default.
• W3100968126 hasConceptScore W3100968126C152671427 @default.
• W3100968126 hasConceptScore W3100968126C153180895 @default.
• W3100968126 hasConceptScore W3100968126C154945302 @default.
• W3100968126 hasConceptScore W3100968126C158693339 @default.
• W3100968126 hasConceptScore W3100968126C163294075 @default.
• W3100968126 hasConceptScore W3100968126C167966045 @default.
• W3100968126 hasConceptScore W3100968126C177148314 @default.
• W3100968126 hasConceptScore W3100968126C2776182073 @default.
• W3100968126 hasConceptScore W3100968126C28490314 @default.
• W3100968126 hasConceptScore W3100968126C33923547 @default.
• W3100968126 hasConceptScore W3100968126C39890363 @default.
• W3100968126 hasConceptScore W3100968126C41008148 @default.
• W3100968126 hasConceptScore W3100968126C42355184 @default.
• W3100968126 hasConceptScore W3100968126C50644808 @default.
• W3100968126 hasConceptScore W3100968126C62520636 @default.
• W3100968126 hasConceptScore W3100968126C8038995 @default.
• W3100968126 hasConceptScore W3100968126C99498987 @default.
• W3100968126 hasLocation W31009681261 @default.
• W3100968126 hasLocation W31009681262 @default.
• W3100968126 hasLocation W31009681263 @default.
• W3100968126 hasLocation W31009681264 @default.
• W3100968126 hasLocation W31009681265 @default.
• W3100968126 hasOpenAccess W3100968126 @default.
• W3100968126 hasPrimaryLocation W31009681261 @default.
• W3100968126 hasRelatedWork W2292254049 @default.
• W3100968126 hasRelatedWork W2405184167 @default.
• W3100968126 hasRelatedWork W2482610912 @default.
• W3100968126 hasRelatedWork W2539994084 @default.
• W3100968126 hasRelatedWork W2592385986 @default.
• W3100968126 hasRelatedWork W2766672686 @default.
• W3100968126 hasRelatedWork W2998100475 @default.

• next