Narrow Results

In this paper, a novel speech recognition method is proposed to improve the recognition efficiency and accuracy of English translators in noisy environments. First, by using an efficient noise suppression algorithm, the interference of background noise to the recognition process is significantly reduced. Then, deep neural networks are used to enhance the adaptability to various noise environments, further improving the stability and accuracy of recognition. In the feature extraction stage, this paper focuses on Mel-Frequency Cepstral Coefficients and Mayer filter bank features, which lays a solid foundation for the application of non-autoregressive Transformer. Finally, non-autoregressive Transformer technology is adopted in this study, which gives full play to its advantages in processing speed and efficiency, ensuring fast and accurate speech recognition in complex noise environments. On the whole, the method in this paper not only improves the performance of speech recognition in noisy environment, but also provides a valuable reference for the research and application in related fields.

Due to the temperature fluctuation, both the self-gravity disturbance level of the gravitational wave detection vehicle and the laser interference measurement system are affected, which brings great noise to the gravitational wave measurement, and the temperature field fluctuation has become one of the most important noise sources of the inertial sensor. In order to ensure the noise level of the inertial sensor to meet the needs of detection, this paper uses the AC bridge to reduce the self-noise of the temperature measurement system, improve the resolution of the temperature measurement system, and realize a high-resolution and low-noise temperature measurement system. The experimental results show that the effective value of self-noise of the temperature measurement system is about 3.65 × 10${{}^{-5}}^{\circ }\text{C}$, and the long-period noise is less than 1 × 10${{}^{-5}}^{\circ }\text{C}$. It can be used in the space gravitational wave detection test and control system.

Cavity noise caused by the high-speed airflow has been paid much attention in the field of aerospace, and the study of cavity noise suppression has an important significance on improving the safety of aircraft. Effects of the leading-edge plate on the flow and the noise of the cavity model (the ratio of length to depth is 6) at a Mach number (Ma) of 0.6 are investigated with high-speed wind tunnel experiment. The acoustic and the flow field information in the cavity are obtained with the dynamic/static pressure measurement and oil flow experiment. The result shows that the leading-edge plate can greatly lift the shear layer, raise the impact position on the back-wall area, and reduce the flux rate and intensity in the cavity. With the controlling of leading-edge plate, the static pressure and backflow area are effectively suppressed and the SPL and peak noise also fall down significantly. The leading-edge plate provides a new method for cavity noise suppression in subsonic flow condition, which can be effectively applied to flow/noise controlling of cavity structure on aircraft.

The joint denoising method using multi-scale wavelet based on threshold value judgment and recursive least-squares (RLS) were proposed to realize lithium battery film thickness measurement. Continuous thickness measurement of thin film coating can be done via threshold value judgment. Low-frequency noise component similar to characters of film thickness can be reduced via RLS denoising. Joint denoising can further improve measurement accuracy. Compared with multi-scale wavelet denoising, the method proposed can improve the measurement precision by 6% which is more suitable to the thickness measurement of film coating.

Images of different origin contain textures, and textural features in such regions are frequently employed in pattern recognition, image classification, information extraction, etc. Noise often present in analyzed images might prevent a proper solution of basic tasks in the aforementioned applications and is worth suppressing. This is not an easy task since even the most advanced denoising methods destroy texture in a more or less degree while removing noise. Thus, it is desirable to predict the filtering behavior before any denoising is applied. This paper studies the efficiency of texture image denoising for different noise intensities and several filter types under different visual quality criteria (quality metrics). It is demonstrated that the most efficient existing filters provide very similar results. From the obtained results, it is possible to generalize and employ the prediction strategy earlier proposed for denoising techniques based on the discrete cosine transform. Accuracy of such a prediction is studied and the ways to improve it are considered. Some practical recommendations concerning a decision to undertake whether it is worth applying a filter are given.

In image enhancement, maintaining the texture and attenuating noise are worth discussing. To address these problems, we propose a low-light image enhancement method with contrast increase and illumination smooth. First, we calculate the maximum map and the minimum map of RGB channels, and then we set maximum map as the initial value for illumination and introduce minimum map to smooth illumination. Second, we use the histogram-equalized version of the input image to construct the weight for the illumination map. Third, we propose an optimization problem to obtain the smooth illumination and refined reflectance. Experimental results show that our method can achieve better performance compared to the state-of-the-art methods.

This work presents a method for background removal and signal-to-noise ratio enhancement by an accumulation of signal and noise along analyzed spectrum. In this case, the signals are accumulated, and noise, due to its chaotic nature, is suppressed. The method is applied to analyze spectra obtained on DRON-6 diffractometer for study of the crystal structure of thin tin dioxide films produced by sol–gel technology and deposited on a glass substrate. The standard analysis of the crystallographic planes of the samples under study is practically impossible due to the high noise level and the negative influence of the background from the glass substrate. The proposed method transformed the initial spectrum, which cannot be analyzed, into an informative spectrum: the background signal from the substrate is correctly subtracted and the noise decreases by 10 times. To check for possible signal distortion due to accumulation signal along the spectrum, an analysis of simulated spectra was carried out. The onset of the transition of an amorphous state to a crystalline structure of SnO₂ is investigated. The crystalline structure of SnO₂ thin films depending on the annealing temperature is studied.

Dance movement is intrinsically connected to the rhythm of music and is a fundamental form of nonverbal communication present in daily human interactions. In order to enable robots to interact with humans in natural real-world environments through dance, these robots must be able to listen to music while robustly tracking the beat of continuous musical stimuli and simultaneously responding to human speech. In this paper, we propose the integration of a real-time beat tracking system with state recovery with different preprocessing solutions used in robot audition for its application to interactive dancing robots. The proposed system is assessed under different real-world acoustic conditions of increasing complexity, which consider multiple audio sources of different kinds, multiple noise sources of different natures, continuous musical and speech stimuli, and the effects of beat-synchronous ego-motion noise and of jittering in ego noise (EN). The overall results suggest improved beat tracking accuracy with lower reaction times to music transitions, while still enhancing automatic speech recognition (ASR) run in parallel in the most challenging conditions. These results corroborate the application of the proposed system for interactive dancing robots.