1-6hit |
Yang WANG Hongliang FU Huawei TAO Jing YANG Hongyi GE Yue XIE
This letter focuses on the cross-corpus speech emotion recognition (SER) task, in which the training and testing speech signals in cross-corpus SER belong to different speech corpora. Existing algorithms are incapable of effectively extracting common sentiment information between different corpora to facilitate knowledge transfer. To address this challenging problem, a novel convolutional auto-encoder and adversarial domain adaptation (CAEADA) framework for cross-corpus SER is proposed. The framework first constructs a one-dimensional convolutional auto-encoder (1D-CAE) for feature processing, which can explore the correlation among adjacent one-dimensional statistic features and the feature representation can be enhanced by the architecture based on encoder-decoder-style. Subsequently the adversarial domain adaptation (ADA) module alleviates the feature distributions discrepancy between the source and target domains by confusing domain discriminator, and specifically employs maximum mean discrepancy (MMD) to better accomplish feature transformation. To evaluate the proposed CAEADA, extensive experiments were conducted on EmoDB, eNTERFACE, and CASIA speech corpora, and the results show that the proposed method outperformed other approaches.
Yutao DONG Xiangzhong FANG Jing YANG
This letter proposes a new algorithm of refining the quantization parameter in H.264 real-time encoding. In the H.264 encoding, the quantization parameter computed according to the quadratic rate model is not accurate in meeting the target bit rate. In order to make the actual encoded bit rate closer to the target bit rate, ρ-domain rate model is introduced in our proposed quantization parameter refinement algorithm. Simulation results show that the proposed algorithm achieves obvious gain in PSNR and has stabler encoded bit rate compared to Jiang's algorithm.
Yutao DONG Xiangzhong FANG Jing YANG
The frame-level R-D optimization in H.264 is very important in video storage scenarios. Among all of the sub-optimal algorithms, a greedy iteration algorithm (GIA) can best lower the computational complexity of frame-level R-D optimization. In order to further lower the computational complexity, a ρ-domain frame-level R-D optimization algorithm is proposed in this letter. Different from GIA, every frame's rate and distortion can be estimated accurately without actual encoding in our proposed algorithm. Simulation results show that our proposed algorithm can lower the computational complexity greatly with negligible variation in peak signal-to-noise ratio (PSNR) compared with GIA.
The selection of motion vectors plays an important role in the error propagation process between inter-frames. In this letter, an end-to-end prediction error calculation method is proposed and is used for the rate-distortion optimized selection of motion vectors. Simulation results show that the robustness of encoded video streams under error-prone environment is improved.
Jun CHAI Mei WEN Nan WU Dafei HUANG Jing YANG Xing CAI Chunyuan ZHANG Qianming YANG
This paper presents a study of the applicability of clusters of GPUs to high-resolution 3D simulations of cardiac electrophysiology. By experimenting with representative cardiac cell models and ODE solvers, in association with solving the monodomain equation, we quantitatively analyze the obtainable computational capacity of GPU clusters. It is found that for a 501×501×101 3D mesh, which entails a 0.1mm spatial resolution, a 128-GPU cluster only needs a few minutes to carry out a 100,000-time-step cardiac excitation simulation that involves a four-variable cell model. Even higher spatial and temporal resolutions are achievable for such simplified mathematical models. On the other hand, our experiments also show that a dramatically larger cluster of GPUs is needed to handle a very detailed cardiac cell model.
Jingjing YANG Yuchun GUO Yishuai CHEN
Microservice architecture has been widely adopted for large-scale applications because of its benefits of scalability, flexibility, and reliability. However, microservice architecture also proposes new challenges in diagnosing root causes of performance degradation. Existing methods rely on labeled data and suffer a high computation burden. This paper proposes MicroState, an unsupervised and lightweight method to pinpoint the root cause with detailed descriptions. We decompose root cause diagnosis into element location and detailed reason identification. To mitigate the impact of element heterogeneity and dynamic invocations, MicroState generates elements' invoked states, quantifies elements' abnormality by warping-based state comparison, and infers the anomalous group. MicroState locates the root cause element with the consideration of anomaly frequency and persistency. To locate the anomalous metric from diverse metrics, MicroState extracts metrics' trend features and evaluates metrics' abnormality based on their trend feature variation, which reduces the reliance on anomaly detectors. Our experimental evaluation based on public data of the Artificial intelligence for IT Operations Challenge (AIOps Challenge 2020) shows that MicroState locates root cause elements with 87% precision and diagnoses anomaly reasons accurately.