FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382725773> ?p ?o ?g. }

• W4382725773 endingPage "66994" @default.
• W4382725773 startingPage "66979" @default.
• W4382725773 abstract "Speech enhancement (SE) is a critical aspect of various speech-processing applications. Recent research in this field focuses on identifying effective ways to capture the long-term contextual dependencies of speech signals to enhance performance. Deep convolutional networks (DCN) using self-attention and the Transformer model have demonstrated competitive results in SE. Transformer models with convolution layers can capture short and long-term temporal sequences by leveraging multi-head self-attention, which allows the model to attend the entire sequence. This study proposes a neural speech enhancement (NSE) using the convolutional encoder-decoder (CED) and convolutional attention Transformer (CAT), named the NSE-CATNet. To effectively process the time-frequency (T-F) distribution of spectral components in speech signals, a T-F attention module is incorporated into the convolutional Transformer model. This module enables the model to explicitly leverage position information and generate a two-dimensional attention map for the time-frequency speech distribution. The performance of the proposed SE is evaluated using objective speech quality and intelligibility metrics on two different datasets, the VoiceBank-DEMAND Corpus and the LibriSpeech dataset. The experimental results indicate that the proposed SE outperformed the competitive baselines in terms of speech enhancement performance at - 5dB, 0dB, and 5dB. This suggests that the model is effective at improving the overall quality by 0.704 with VoiceBank-DEMAND and by 0.692 with LibriSpeech. Further, the intelligibility with VoiceBank-DEMAND and LibriSpeech is improved by 11.325% and 11.75% over the noisy speech signals." @default.
• W4382725773 created "2023-07-01" @default.
• W4382725773 creator A5026642878 @default.
• W4382725773 creator A5031234998 @default.
• W4382725773 creator A5040003632 @default.
• W4382725773 creator A5059780753 @default.
• W4382725773 creator A5077120203 @default.
• W4382725773 date "2023-01-01" @default.
• W4382725773 modified "2023-09-25" @default.
• W4382725773 title "NSE-CATNet: Deep Neural Speech Enhancement Using Convolutional Attention Transformer Network" @default.
• W4382725773 cites W1494198834 @default.
• W4382725773 cites W1506438021 @default.
• W4382725773 cites W1974387177 @default.
• W4382725773 cites W2006910250 @default.
• W4382725773 cites W2038484192 @default.
• W4382725773 cites W2044893557 @default.
• W4382725773 cites W2063378142 @default.
• W4382725773 cites W2067295501 @default.
• W4382725773 cites W2069681747 @default.
• W4382725773 cites W2078528584 @default.
• W4382725773 cites W2128653836 @default.
• W4382725773 cites W2144404214 @default.
• W4382725773 cites W2168379380 @default.
• W4382725773 cites W2291877678 @default.
• W4382725773 cites W2364134690 @default.
• W4382725773 cites W2405774341 @default.
• W4382725773 cites W2602577565 @default.
• W4382725773 cites W2774389566 @default.
• W4382725773 cites W2889442120 @default.
• W4382725773 cites W2889890482 @default.
• W4382725773 cites W2921144622 @default.
• W4382725773 cites W2937484199 @default.
• W4382725773 cites W2940275453 @default.
• W4382725773 cites W2945191446 @default.
• W4382725773 cites W2954198060 @default.
• W4382725773 cites W2962843322 @default.
• W4382725773 cites W2963341071 @default.
• W4382725773 cites W2973006943 @default.
• W4382725773 cites W2991361823 @default.
• W4382725773 cites W2998445964 @default.
• W4382725773 cites W3015844538 @default.
• W4382725773 cites W3016129867 @default.
• W4382725773 cites W3016447038 @default.
• W4382725773 cites W3017350693 @default.
• W4382725773 cites W3081608966 @default.
• W4382725773 cites W3086513098 @default.
• W4382725773 cites W3095057960 @default.
• W4382725773 cites W3096408984 @default.
• W4382725773 cites W3097945073 @default.
• W4382725773 cites W3109018774 @default.
• W4382725773 cites W3109196171 @default.
• W4382725773 cites W3117290926 @default.
• W4382725773 cites W3120336970 @default.
• W4382725773 cites W3121098269 @default.
• W4382725773 cites W3135881253 @default.
• W4382725773 cites W3147539069 @default.
• W4382725773 cites W3160129476 @default.
• W4382725773 cites W3161950572 @default.
• W4382725773 cites W3162493033 @default.
• W4382725773 cites W3165858867 @default.
• W4382725773 cites W3177067699 @default.
• W4382725773 cites W3197729725 @default.
• W4382725773 cites W3197822518 @default.
• W4382725773 cites W3197912330 @default.
• W4382725773 cites W3213188934 @default.
• W4382725773 cites W4200079780 @default.
• W4382725773 cites W4285791551 @default.
• W4382725773 cites W4296276529 @default.
• W4382725773 cites W4306160625 @default.
• W4382725773 cites W4312271884 @default.
• W4382725773 cites W4315606033 @default.
• W4382725773 cites W4318975163 @default.
• W4382725773 cites W4319295650 @default.
• W4382725773 cites W4323338563 @default.
• W4382725773 doi "https://doi.org/10.1109/access.2023.3290908" @default.
• W4382725773 hasPublicationYear "2023" @default.
• W4382725773 type Work @default.
• W4382725773 citedByCount "0" @default.
• W4382725773 crossrefType "journal-article" @default.
• W4382725773 hasAuthorship W4382725773A5026642878 @default.
• W4382725773 hasAuthorship W4382725773A5031234998 @default.
• W4382725773 hasAuthorship W4382725773A5040003632 @default.
• W4382725773 hasAuthorship W4382725773A5059780753 @default.
• W4382725773 hasAuthorship W4382725773A5077120203 @default.
• W4382725773 hasBestOaLocation W43827257731 @default.
• W4382725773 hasConcept C111472728 @default.
• W4382725773 hasConcept C111919701 @default.
• W4382725773 hasConcept C118505674 @default.
• W4382725773 hasConcept C121332964 @default.
• W4382725773 hasConcept C138885662 @default.
• W4382725773 hasConcept C154945302 @default.
• W4382725773 hasConcept C163294075 @default.
• W4382725773 hasConcept C165801399 @default.
• W4382725773 hasConcept C2776182073 @default.
• W4382725773 hasConcept C28490314 @default.
• W4382725773 hasConcept C41008148 @default.
• W4382725773 hasConcept C60048801 @default.
• W4382725773 hasConcept C62520636 @default.

• next