International Journal of Computer Vision - Face recognition has been significantly advanced by deep learning based methods. In all face recognition methods based on convolutional neural network... 相似文献
Human beings are capable of imagining a person’s voice according to his or her appearance because different people have different voice characteristics. Although researchers have made great progress in single-view speech synthesis, there are few studies on multi-view speech synthesis, especially the speech synthesis using face images. On the basis of implicit relationship between the speaker’s face image and his or her voice, we propose a multi-view speech synthesis method called SSFE (Speech Synthesis with Face Embeddings). The proposed SSFE consists of three parts: a voice encoder, a face encoder and an improved multi-speaker text-to-speech (TTS) engine. On the one hand, the proposed voice encoder generates the voice embeddings from the speaker’s speech and the proposed face encoder extracts the voice features from the speaker’s face as f-voice embeddings. On the other hand, the multi-speaker TTS engine would synthesize the speech with voice embeddings and f-voice embeddings. We have conducted extensive experiments to evaluate the proposed SSFE on the synthesized speech quality and face-voice matching degree, in which the Mean Opinion Score of the SSFE is more than 3.7 and the matching degree is about 1.7. The experimental results prove that the proposed SSFE method outperforms state-of-the-art methods on the synthesized speech in terms of speech quality and face-voice matching degree.
Applied Intelligence - Face aging is of great significance in cross-time identity verification problem. However, there is still a huge gap between the synthesized face image and the real face in... 相似文献
Due to air turbulence, large areas of coal will fall when the special coal-transportation trains pass the tunnel exits and entrances. Aiming at the problems of low efficiency and high cost of manual cleaning for long distance coal cleaning in the tunnel, a new railway tunnel fallen coal dust collection device which was composed of a main conveying coal feeding pipe and multiple branch pipes of coal suction was designed. It was used to clean the small particles and lightweight railway tunnel fallen coal. Firstly, the gas-solid two-phase flow model based on the Euler-Lagrange approach for the design of the main conveying coal feeding pipe was established in the coal conveying pipelines. Secondly, the effect of the coal particles' incident angle and multiple branch pipe spacing on the main coal conveying pipe flow field, which was based on Fluent finite element simulation software, was studied. What was more, the optimal angle of incidence and the optimal value of the number of branch coal suction pipe, which was installed on the main conveying pipe, were analyzed. Finally, the finite element simulation was verified by field test. Simulation and experimental results showed that it was more conducive to the railway tunnel fallen coal transportation when coal particles' incident angle was less than 45° and the branch pipe spacing was in the vicinity of 750 mm. For that when incident angle was less than 45°, the main conveying coal pipe pressure-drop became weaker and particle flow could obtain large horizontal transport velocity. And when the branch pipe spacing was in the vicinity of 750 mm, the horizontal transport velocity had a smaller fluctuation range and the transportation of coal was larger than that of the other groups. The research results are of great significance to improve the structure of the main conveying coal pipe, increase the efficiency of tunnel coal conveying and optimize the railway tunnel coal dust collection device. 相似文献
We investigate the dynamics of granular flows under the action of a centrifugal acceleration field. The granular flows consist of a monodisperse set of glass beads flowing down an inclined plane. The experiments are performed at variable slope angles \(\zeta \) and equivalent centrifugal accelerations \(a_\text {cf}\equiv Ng\). We study the effect of this parameters on the superficial flow velocity u and flow height h. Two trends are observed, by increasing \(\zeta \) and \(a_\text {cf}\), u increases proportionally, and h decreases asymptotically until a constant height. This relation is analysed in terms of the system potential and kinetic energy, leading to the estimation of equivalent impact forces one order of magnitude larger than those observed in small scale 1g laboratory experiments, with the possibility to reach higher forces by increasing N. Finally, considering the trend of u and h, our results suggest a scaling principle of inertial velocity proportional to \(\sqrt{N}\). 相似文献
An analytical solution for simply supported layered plates with viscoelastic interlayers under a transverse load is proposed. The deformation of each plate layer is described by the exact three-dimensional elasticity equations. The viscoelastic property of interlayer is simulated by the generalized Maxwell model. The constitutive relation of the interlayer is simplified by the quasi-elastic approximation, which significantly simplifies the analytical process. The solution of stress and displacement fields with undetermined coefficients is derived by solving a group of ordinary differential equations. The undetermined coefficients can be efficiently deduced by using the recursive matrix technique for the plate with any number of layers. The practical convergence is observed during numerical tests. The comparison analysis indicates that the present solution has a close agreement with the finite element solution. However, the solution based on the Mindlin–Reissner hypothesis is significantly different from the present solution for thick plates. Finally, the effect of interlayer thickness on stress and displacement distributions of a five-layer plate is discussed in detail. 相似文献