FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384558081> ?p ?o ?g. }

• W4384558081 endingPage "3644" @default.
• W4384558081 startingPage "3644" @default.
• W4384558081 abstract "The problem of cleaning impaired speech is crucial for various applications such as speech recognition, telecommunication, and assistive technologies. In this paper, we propose a novel approach that combines Pareto-optimized deep learning with non-negative matrix factorization (NMF) to effectively reduce noise in impaired speech signals while preserving the quality of the desired speech. Our method begins by calculating the spectrogram of a noisy voice clip and extracting frequency statistics. A threshold is then determined based on the desired noise sensitivity, and a noise-to-signal mask is computed. This mask is smoothed to avoid abrupt transitions in noise levels, and the modified spectrogram is obtained by applying the smoothed mask to the signal spectrogram. We then employ a Pareto-optimized NMF to decompose the modified spectrogram into basis functions and corresponding weights, which are used to reconstruct the clean speech spectrogram. The final noise-reduced waveform is obtained by inverting the clean speech spectrogram. Our proposed method achieves a balance between various objectives, such as noise suppression, speech quality preservation, and computational efficiency, by leveraging Pareto optimization in the deep learning model. The experimental results demonstrate the effectiveness of our approach in cleaning alaryngeal speech signals, making it a promising solution for various real-world applications." @default.
• W4384558081 created "2023-07-18" @default.
• W4384558081 creator A5039508726 @default.
• W4384558081 creator A5040140543 @default.
• W4384558081 creator A5042653526 @default.
• W4384558081 creator A5056794751 @default.
• W4384558081 creator A5070081059 @default.
• W4384558081 creator A5092207360 @default.
• W4384558081 date "2023-07-16" @default.
• W4384558081 modified "2023-10-14" @default.
• W4384558081 title "Pareto-Optimized Non-Negative Matrix Factorization Approach to the Cleaning of Alaryngeal Speech Signals" @default.
• W4384558081 cites W1959149127 @default.
• W4384558081 cites W1971656081 @default.
• W4384558081 cites W1979754637 @default.
• W4384558081 cites W1992321269 @default.
• W4384558081 cites W2000328903 @default.
• W4384558081 cites W2022823908 @default.
• W4384558081 cites W2032532974 @default.
• W4384558081 cites W2043414444 @default.
• W4384558081 cites W2048646122 @default.
• W4384558081 cites W2061234361 @default.
• W4384558081 cites W2065842649 @default.
• W4384558081 cites W2068452295 @default.
• W4384558081 cites W2070462850 @default.
• W4384558081 cites W2077297627 @default.
• W4384558081 cites W2083899124 @default.
• W4384558081 cites W2110520761 @default.
• W4384558081 cites W2112998453 @default.
• W4384558081 cites W2124653604 @default.
• W4384558081 cites W2155476965 @default.
• W4384558081 cites W2160927412 @default.
• W4384558081 cites W2557888310 @default.
• W4384558081 cites W2724903827 @default.
• W4384558081 cites W2760047129 @default.
• W4384558081 cites W2766490547 @default.
• W4384558081 cites W2769827215 @default.
• W4384558081 cites W2771030776 @default.
• W4384558081 cites W2783831802 @default.
• W4384558081 cites W2786889008 @default.
• W4384558081 cites W2891234302 @default.
• W4384558081 cites W2911043226 @default.
• W4384558081 cites W2933389261 @default.
• W4384558081 cites W2949795487 @default.
• W4384558081 cites W2952939215 @default.
• W4384558081 cites W2962795274 @default.
• W4384558081 cites W2968591836 @default.
• W4384558081 cites W2972471162 @default.
• W4384558081 cites W2972785266 @default.
• W4384558081 cites W2985349381 @default.
• W4384558081 cites W2998616931 @default.
• W4384558081 cites W2999492576 @default.
• W4384558081 cites W3001387854 @default.
• W4384558081 cites W3005302394 @default.
• W4384558081 cites W3016030932 @default.
• W4384558081 cites W3033141596 @default.
• W4384558081 cites W3036136559 @default.
• W4384558081 cites W3045107796 @default.
• W4384558081 cites W3080185952 @default.
• W4384558081 cites W3085680681 @default.
• W4384558081 cites W3094604100 @default.
• W4384558081 cites W3112225841 @default.
• W4384558081 cites W3114898335 @default.
• W4384558081 cites W3118682431 @default.
• W4384558081 cites W3119041615 @default.
• W4384558081 cites W3125610266 @default.
• W4384558081 cites W3127339759 @default.
• W4384558081 cites W3130967494 @default.
• W4384558081 cites W3159719190 @default.
• W4384558081 cites W3187212676 @default.
• W4384558081 cites W3193024559 @default.
• W4384558081 cites W3201279130 @default.
• W4384558081 cites W3202568147 @default.
• W4384558081 cites W3204191733 @default.
• W4384558081 cites W3209110707 @default.
• W4384558081 cites W3215701596 @default.
• W4384558081 cites W4200549429 @default.
• W4384558081 cites W4205871952 @default.
• W4384558081 cites W4210358886 @default.
• W4384558081 cites W4210553839 @default.
• W4384558081 cites W4220774397 @default.
• W4384558081 cites W4221094122 @default.
• W4384558081 cites W4223646484 @default.
• W4384558081 cites W4225672229 @default.
• W4384558081 cites W4280649558 @default.
• W4384558081 cites W4281952231 @default.
• W4384558081 cites W4285077312 @default.
• W4384558081 cites W4285728831 @default.
• W4384558081 cites W4286496634 @default.
• W4384558081 cites W4289336416 @default.
• W4384558081 cites W4290993849 @default.
• W4384558081 cites W4294844716 @default.
• W4384558081 cites W4297521812 @default.
• W4384558081 cites W4297841464 @default.
• W4384558081 cites W4308186239 @default.
• W4384558081 cites W4309311518 @default.
• W4384558081 cites W4313329129 @default.
• W4384558081 cites W4323345614 @default.
• W4384558081 cites W4327935670 @default.

• next