Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385841084> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4385841084 endingPage "109582" @default.
- W4385841084 startingPage "109582" @default.
- W4385841084 abstract "The field of speech bandwidth extension (BWE) has witnessed remarkable advancements through the implementation of convolutional neural networks (CNNs). However, one limitation of CNNs is the lack of consideration for the strong correlation between different frames of speech signals. Effectively utilizing the inter-frame features and sample points has become an urgent challenge that needs to be addressed in this context. To address this problem, we propose an improved time–frequency network that combines spatial attention module and batch attention module. Our proposed approach involves a spatial attention module that uses multi-layer dilated convolutions to capture spatial dependencies in feature maps. Additionally, a batch attention module utilizes pooling and fully connected operations to leverage the correlation between speech frames. We introduce a time–frequency (T-F) loss to optimize the amplitude and phase of reconstructed speech signals, reducing artificial artifacts. Experimental results demonstrate the superiority of our network compared to other baseline BWE networks on four datasets, as measured by SNR, LSD, PESQ, and MOS metrics. Notably, on the TIMIT dataset, our network with the T-F loss achieves superior LSD and SNR values over other loss functions." @default.
- W4385841084 created "2023-08-16" @default.
- W4385841084 creator A5002302868 @default.
- W4385841084 creator A5002316942 @default.
- W4385841084 creator A5078953146 @default.
- W4385841084 date "2023-08-01" @default.
- W4385841084 modified "2023-10-09" @default.
- W4385841084 title "Time-frequency network combining batch attention and spatial attention for speech bandwidth extension" @default.
- W4385841084 cites W1517841224 @default.
- W4385841084 cites W1745334888 @default.
- W4385841084 cites W1971868317 @default.
- W4385841084 cites W1994997782 @default.
- W4385841084 cites W2401383940 @default.
- W4385841084 cites W2534867751 @default.
- W4385841084 cites W2752782242 @default.
- W4385841084 cites W2761952131 @default.
- W4385841084 cites W2784918340 @default.
- W4385841084 cites W2802034954 @default.
- W4385841084 cites W2892335023 @default.
- W4385841084 cites W2940120659 @default.
- W4385841084 cites W2943554574 @default.
- W4385841084 cites W2963091558 @default.
- W4385841084 cites W2963242190 @default.
- W4385841084 cites W2998639482 @default.
- W4385841084 cites W3015368254 @default.
- W4385841084 cites W3016166140 @default.
- W4385841084 cites W3102195007 @default.
- W4385841084 cites W3196416517 @default.
- W4385841084 doi "https://doi.org/10.1016/j.apacoust.2023.109582" @default.
- W4385841084 hasPublicationYear "2023" @default.
- W4385841084 type Work @default.
- W4385841084 citedByCount "0" @default.
- W4385841084 crossrefType "journal-article" @default.
- W4385841084 hasAuthorship W4385841084A5002302868 @default.
- W4385841084 hasAuthorship W4385841084A5002316942 @default.
- W4385841084 hasAuthorship W4385841084A5078953146 @default.
- W4385841084 hasBestOaLocation W43858410841 @default.
- W4385841084 hasConcept C103734657 @default.
- W4385841084 hasConcept C153083717 @default.
- W4385841084 hasConcept C153180895 @default.
- W4385841084 hasConcept C154945302 @default.
- W4385841084 hasConcept C163294075 @default.
- W4385841084 hasConcept C23224414 @default.
- W4385841084 hasConcept C2776182073 @default.
- W4385841084 hasConcept C2776257435 @default.
- W4385841084 hasConcept C2778724510 @default.
- W4385841084 hasConcept C28490314 @default.
- W4385841084 hasConcept C31258907 @default.
- W4385841084 hasConcept C41008148 @default.
- W4385841084 hasConcept C70437156 @default.
- W4385841084 hasConcept C81363708 @default.
- W4385841084 hasConceptScore W4385841084C103734657 @default.
- W4385841084 hasConceptScore W4385841084C153083717 @default.
- W4385841084 hasConceptScore W4385841084C153180895 @default.
- W4385841084 hasConceptScore W4385841084C154945302 @default.
- W4385841084 hasConceptScore W4385841084C163294075 @default.
- W4385841084 hasConceptScore W4385841084C23224414 @default.
- W4385841084 hasConceptScore W4385841084C2776182073 @default.
- W4385841084 hasConceptScore W4385841084C2776257435 @default.
- W4385841084 hasConceptScore W4385841084C2778724510 @default.
- W4385841084 hasConceptScore W4385841084C28490314 @default.
- W4385841084 hasConceptScore W4385841084C31258907 @default.
- W4385841084 hasConceptScore W4385841084C41008148 @default.
- W4385841084 hasConceptScore W4385841084C70437156 @default.
- W4385841084 hasConceptScore W4385841084C81363708 @default.
- W4385841084 hasFunder F4320321001 @default.
- W4385841084 hasLocation W43858410841 @default.
- W4385841084 hasOpenAccess W4385841084 @default.
- W4385841084 hasPrimaryLocation W43858410841 @default.
- W4385841084 hasRelatedWork W1973895194 @default.
- W4385841084 hasRelatedWork W1980687383 @default.
- W4385841084 hasRelatedWork W2058482658 @default.
- W4385841084 hasRelatedWork W2105126898 @default.
- W4385841084 hasRelatedWork W2153897396 @default.
- W4385841084 hasRelatedWork W2345688450 @default.
- W4385841084 hasRelatedWork W3016109656 @default.
- W4385841084 hasRelatedWork W3135613579 @default.
- W4385841084 hasRelatedWork W3209446892 @default.
- W4385841084 hasRelatedWork W4386746628 @default.
- W4385841084 hasVolume "211" @default.
- W4385841084 isParatext "false" @default.
- W4385841084 isRetracted "false" @default.
- W4385841084 workType "article" @default.