Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385800720> ?p ?o ?g. }
- W4385800720 abstract "Abstract The presence of noise and reverberation significantly impedes speech clarity and intelligibility. To mitigate these effects, numerous deep learning-based network models have been proposed for speech enhancement tasks aimed at improving speech quality. In this study, we propose a monaural speech enhancement model called the channel and temporal-frequency attention UNet (CTFUNet). CTFUNet takes the noisy spectrum as input and produces a complex ideal ratio mask (cIRM) as output. To improve the speech enhancement performance of CTFUNet, we employ multi-scale temporal-frequency processing to extract input speech spectrum features. We also utilize multi-conv head channel attention and residual channel attention to capture temporal-frequency and channel features. Moreover, we introduce the channel temporal-frequency skip connection to alleviate information loss between down-sampling and up-sampling. On the blind test set of the first deep noise suppression challenge, our proposed CTFUNet has better denoising performance than the champion models and the latest models. Furthermore, our model outperforms recent models such as Uformar and MTFAA in both denoising and dereverberation performance." @default.
- W4385800720 created "2023-08-15" @default.
- W4385800720 creator A5009651653 @default.
- W4385800720 creator A5086533417 @default.
- W4385800720 creator A5090668921 @default.
- W4385800720 date "2023-08-14" @default.
- W4385800720 modified "2023-10-11" @default.
- W4385800720 title "Channel and temporal-frequency attention UNet for monaural speech enhancement" @default.
- W4385800720 cites W1901129140 @default.
- W4385800720 cites W1998648683 @default.
- W4385800720 cites W2013590534 @default.
- W4385800720 cites W2115613106 @default.
- W4385800720 cites W2121973264 @default.
- W4385800720 cites W2125114513 @default.
- W4385800720 cites W2127851351 @default.
- W4385800720 cites W2141998673 @default.
- W4385800720 cites W2143612262 @default.
- W4385800720 cites W2678916739 @default.
- W4385800720 cites W2752782242 @default.
- W4385800720 cites W2866634454 @default.
- W4385800720 cites W2884585870 @default.
- W4385800720 cites W2937484199 @default.
- W4385800720 cites W2940275453 @default.
- W4385800720 cites W2952218014 @default.
- W4385800720 cites W2963103134 @default.
- W4385800720 cites W2991361823 @default.
- W4385800720 cites W2998161426 @default.
- W4385800720 cites W3016129867 @default.
- W4385800720 cites W3019433526 @default.
- W4385800720 cites W3096408984 @default.
- W4385800720 cites W3096641561 @default.
- W4385800720 cites W3097034112 @default.
- W4385800720 cites W3097777922 @default.
- W4385800720 cites W3097906045 @default.
- W4385800720 cites W3113290170 @default.
- W4385800720 cites W3120336970 @default.
- W4385800720 cites W3134695619 @default.
- W4385800720 cites W3147539069 @default.
- W4385800720 cites W3160085755 @default.
- W4385800720 cites W3161140524 @default.
- W4385800720 cites W3162493033 @default.
- W4385800720 cites W3162501355 @default.
- W4385800720 cites W3190196596 @default.
- W4385800720 cites W3198680319 @default.
- W4385800720 cites W3211408542 @default.
- W4385800720 cites W3212231398 @default.
- W4385800720 cites W3213188934 @default.
- W4385800720 cites W4221149546 @default.
- W4385800720 cites W4224932531 @default.
- W4385800720 cites W4224934178 @default.
- W4385800720 cites W4225302959 @default.
- W4385800720 cites W4225672218 @default.
- W4385800720 cites W4297841575 @default.
- W4385800720 cites W4312678820 @default.
- W4385800720 cites W4372346224 @default.
- W4385800720 cites W4375869009 @default.
- W4385800720 doi "https://doi.org/10.1186/s13636-023-00295-6" @default.
- W4385800720 hasPublicationYear "2023" @default.
- W4385800720 type Work @default.
- W4385800720 citedByCount "0" @default.
- W4385800720 crossrefType "journal-article" @default.
- W4385800720 hasAuthorship W4385800720A5009651653 @default.
- W4385800720 hasAuthorship W4385800720A5086533417 @default.
- W4385800720 hasAuthorship W4385800720A5090668921 @default.
- W4385800720 hasBestOaLocation W43858007201 @default.
- W4385800720 hasConcept C102894143 @default.
- W4385800720 hasConcept C111472728 @default.
- W4385800720 hasConcept C121332964 @default.
- W4385800720 hasConcept C127162648 @default.
- W4385800720 hasConcept C138885662 @default.
- W4385800720 hasConcept C154945302 @default.
- W4385800720 hasConcept C163294075 @default.
- W4385800720 hasConcept C24890656 @default.
- W4385800720 hasConcept C2776182073 @default.
- W4385800720 hasConcept C28490314 @default.
- W4385800720 hasConcept C41008148 @default.
- W4385800720 hasConcept C60048801 @default.
- W4385800720 hasConcept C76155785 @default.
- W4385800720 hasConcept C95851461 @default.
- W4385800720 hasConceptScore W4385800720C102894143 @default.
- W4385800720 hasConceptScore W4385800720C111472728 @default.
- W4385800720 hasConceptScore W4385800720C121332964 @default.
- W4385800720 hasConceptScore W4385800720C127162648 @default.
- W4385800720 hasConceptScore W4385800720C138885662 @default.
- W4385800720 hasConceptScore W4385800720C154945302 @default.
- W4385800720 hasConceptScore W4385800720C163294075 @default.
- W4385800720 hasConceptScore W4385800720C24890656 @default.
- W4385800720 hasConceptScore W4385800720C2776182073 @default.
- W4385800720 hasConceptScore W4385800720C28490314 @default.
- W4385800720 hasConceptScore W4385800720C41008148 @default.
- W4385800720 hasConceptScore W4385800720C60048801 @default.
- W4385800720 hasConceptScore W4385800720C76155785 @default.
- W4385800720 hasConceptScore W4385800720C95851461 @default.
- W4385800720 hasFunder F4320321001 @default.
- W4385800720 hasFunder F4320321921 @default.
- W4385800720 hasIssue "1" @default.
- W4385800720 hasLocation W43858007201 @default.
- W4385800720 hasOpenAccess W4385800720 @default.
- W4385800720 hasPrimaryLocation W43858007201 @default.
- W4385800720 hasRelatedWork W2046186789 @default.