FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384131022> ?p ?o ?g. }

• W4384131022 endingPage "3052" @default.
• W4384131022 startingPage "3052" @default.
• W4384131022 abstract "This paper proposes an innovative single-channel supervised speech enhancement (SE) method based on UNET, a convolutional neural network (CNN) architecture that expands on a few changes in the basic CNN architecture. In the training phase, short-time Fourier transform (STFT) is exploited on the noisy time domain signal to build a noisy time-frequency domain signal which is called a complex noisy matrix. We take the real and imaginary parts of the complex noisy matrix and concatenate both of them to form the noisy concatenated matrix. We apply UNET to the noisy concatenated matrix for extracting speech components and train the CNN model. In the testing phase, the same procedure is applied to the noisy time-domain signal as in the training phase in order to construct another noisy concatenated matrix that can be tested using a pre-trained or saved model in order to construct an enhanced concatenated matrix. Finally, from the enhanced concatenated matrix, we separate both the imaginary and real parts to form an enhanced complex matrix. Magnitude and phase are then extracted from the newly created enhanced complex matrix. By using that magnitude and phase, the inverse STFT (ISTFT) can generate the enhanced speech signal. Utilizing the IEEE databases and various types of noise, including stationary and non-stationary noise, the proposed method is evaluated. Comparing the exploratory results of the proposed algorithm to the other five methods of STFT, sparse non-negative matrix factorization (SNMF), dual-tree complex wavelet transform (DTCWT)-SNMF, DTCWT-STFT-SNMF, STFT-convolutional denoising auto encoder (CDAE) and casual multi-head attention mechanism (CMAM) for speech enhancement, we determine that the proposed algorithm generally improves speech quality and intelligibility at all considered signal-to-noise ratios (SNRs). The suggested approach performs better than the other five competing algorithms in every evaluation metric." @default.
• W4384131022 created "2023-07-14" @default.
• W4384131022 creator A5009607101 @default.
• W4384131022 creator A5013227916 @default.
• W4384131022 creator A5026835889 @default.
• W4384131022 creator A5050520066 @default.
• W4384131022 creator A5068540940 @default.
• W4384131022 creator A5088613791 @default.
• W4384131022 creator A5091462841 @default.
• W4384131022 date "2023-07-12" @default.
• W4384131022 modified "2023-09-27" @default.
• W4384131022 title "Supervised Single Channel Speech Enhancement Method Using UNET" @default.
• W4384131022 cites W1552314771 @default.
• W4384131022 cites W1594771616 @default.
• W4384131022 cites W1902027874 @default.
• W4384131022 cites W1968939597 @default.
• W4384131022 cites W2013608223 @default.
• W4384131022 cites W2044893557 @default.
• W4384131022 cites W2057200980 @default.
• W4384131022 cites W2059745395 @default.
• W4384131022 cites W2092262399 @default.
• W4384131022 cites W2092644348 @default.
• W4384131022 cites W2101304342 @default.
• W4384131022 cites W2109715093 @default.
• W4384131022 cites W2121973264 @default.
• W4384131022 cites W2128653836 @default.
• W4384131022 cites W2141998673 @default.
• W4384131022 cites W2605138598 @default.
• W4384131022 cites W2889669262 @default.
• W4384131022 cites W2891433113 @default.
• W4384131022 cites W2963453742 @default.
• W4384131022 cites W2963828919 @default.
• W4384131022 cites W2975955714 @default.
• W4384131022 cites W3007348697 @default.
• W4384131022 cites W3022404557 @default.
• W4384131022 cites W3100604685 @default.
• W4384131022 cites W3160085755 @default.
• W4384131022 cites W4231807801 @default.
• W4384131022 cites W4253928870 @default.
• W4384131022 cites W4301802631 @default.
• W4384131022 cites W4306377806 @default.
• W4384131022 cites W4308455602 @default.
• W4384131022 cites W4319662288 @default.
• W4384131022 cites W4321019924 @default.
• W4384131022 doi "https://doi.org/10.3390/electronics12143052" @default.
• W4384131022 hasPublicationYear "2023" @default.
• W4384131022 type Work @default.
• W4384131022 citedByCount "0" @default.
• W4384131022 crossrefType "journal-article" @default.
• W4384131022 hasAuthorship W4384131022A5009607101 @default.
• W4384131022 hasAuthorship W4384131022A5013227916 @default.
• W4384131022 hasAuthorship W4384131022A5026835889 @default.
• W4384131022 hasAuthorship W4384131022A5050520066 @default.
• W4384131022 hasAuthorship W4384131022A5068540940 @default.
• W4384131022 hasAuthorship W4384131022A5088613791 @default.
• W4384131022 hasAuthorship W4384131022A5091462841 @default.
• W4384131022 hasBestOaLocation W43841310221 @default.
• W4384131022 hasConcept C102519508 @default.
• W4384131022 hasConcept C106487976 @default.
• W4384131022 hasConcept C11413529 @default.
• W4384131022 hasConcept C115961682 @default.
• W4384131022 hasConcept C121332964 @default.
• W4384131022 hasConcept C134306372 @default.
• W4384131022 hasConcept C153180895 @default.
• W4384131022 hasConcept C154945302 @default.
• W4384131022 hasConcept C158693339 @default.
• W4384131022 hasConcept C159985019 @default.
• W4384131022 hasConcept C163294075 @default.
• W4384131022 hasConcept C166386157 @default.
• W4384131022 hasConcept C192562407 @default.
• W4384131022 hasConcept C196216189 @default.
• W4384131022 hasConcept C203024314 @default.
• W4384131022 hasConcept C2776182073 @default.
• W4384131022 hasConcept C2777885455 @default.
• W4384131022 hasConcept C28490314 @default.
• W4384131022 hasConcept C33923547 @default.
• W4384131022 hasConcept C41008148 @default.
• W4384131022 hasConcept C42355184 @default.
• W4384131022 hasConcept C46286280 @default.
• W4384131022 hasConcept C47432892 @default.
• W4384131022 hasConcept C62520636 @default.
• W4384131022 hasConcept C99498987 @default.
• W4384131022 hasConceptScore W4384131022C102519508 @default.
• W4384131022 hasConceptScore W4384131022C106487976 @default.
• W4384131022 hasConceptScore W4384131022C11413529 @default.
• W4384131022 hasConceptScore W4384131022C115961682 @default.
• W4384131022 hasConceptScore W4384131022C121332964 @default.
• W4384131022 hasConceptScore W4384131022C134306372 @default.
• W4384131022 hasConceptScore W4384131022C153180895 @default.
• W4384131022 hasConceptScore W4384131022C154945302 @default.
• W4384131022 hasConceptScore W4384131022C158693339 @default.
• W4384131022 hasConceptScore W4384131022C159985019 @default.
• W4384131022 hasConceptScore W4384131022C163294075 @default.
• W4384131022 hasConceptScore W4384131022C166386157 @default.
• W4384131022 hasConceptScore W4384131022C192562407 @default.
• W4384131022 hasConceptScore W4384131022C196216189 @default.
• W4384131022 hasConceptScore W4384131022C203024314 @default.
• W4384131022 hasConceptScore W4384131022C2776182073 @default.

• next