1. |
|
|
2. |
|
|
3. |
- Lin, Xiongwei, et al.
(författare)
-
Noise reduction optimization of sound sensor based on a Conditional Generation Adversarial Network
- 2021
-
Ingår i: Journal of Physics: Conference Series. - : IOP Publishing. - 1742-6588 .- 1742-6596. ; 1873:1
-
Konferensbidrag (refereegranskat)abstract
- To address the problems in the traditional speech signal noise elimination methods, such as the residual noise, poor real-time performance and narrow applications a new method is proposed to eliminate network voice noise based on deep learning of conditional generation adversarial network. In terms of the perceptual evaluation of speech quality (PESQ) and shorttime objective intelligibility measure (STOI) functions used as the loss function in the neural network, which were used as the loss function in the neural network, the flexibility of the whole network was optimized, and the training process of the model simplified. The experimental results indicate that, under the noisy environment, especially in a restaurant, the proposed noise reduction scheme improves the STOI score by 26.23% and PESQ score by 17.18%, respectively, compared with the traditional Wiener noise reduction algorithm. Therefore, the sound sensor's noise reduction scheme through our approach has achieved a remarkable noise reduction effect, more useful information transmission, and stronger practicability.
|
|
4. |
- Zhou, Qun Yan, et al.
(författare)
-
Information Metasurface for Simultaneous Wave Manipulations and Signal Modulations
- 2024
-
Ingår i: 18th European Conference on Antennas and Propagation, EuCAP 2024. - : Institute of Electrical and Electronics Engineers (IEEE).
-
Konferensbidrag (refereegranskat)abstract
- Recently, digital and programmable metasurface has evolved into a new branch as information metasurface owing to its real-time manipulation of electromagnetic (EM) waves and simultaneous modulation of digital signals. Here, we present the theoretical model of information metasurface and analyze its capability of wave manipulation and signal modulation. Further, we extend the single-metasurface model into a multi-metasurface one, and discuss the feasibility and application of their joint operation. Our simulation results show its performance in high-precision harmonic scattering patterns, higher-order signal modulation, and spatial localization, demonstrating the potential of information metasurface in wireless communications and radar signal processing.
|
|