Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models. (arXiv:1911.09762v1 [cs.CL])

In this paper, we propose to use pre-trained features from end-to-end ASR models to solve the speech sentiment analysis problem as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from speech, achieve promising results. We use RNN with self-attention as the sentiment classifier, which also provides an…

Continuous and discrete abstractions for planning, applied to ship docking. (arXiv:1911.09773v1 [eess.SY])

We propose a hierarchical control framework for the synthesis of correct-by-construction controllers for nonlinear control-affine systems with respect to reach-avoid-stay specifications. We first create a low-dimensional continuous abstraction of the system and use Sum-of-Squares (SOS) programming to obtain a low-level controller ensuring a bounded error between the two models. We then create a discrete abstraction…

Interval Reachability Analysis using Second-Order Sensitivity. (arXiv:1911.09775v1 [eess.SY])

We propose a new approach to compute an interval over-approximation of the finite time reachable set for a large class of nonlinear systems. This approach relies on the notions of sensitivity matrices, which are the partial derivatives representing the variations of the system trajectories in response to variations of the initial states. Using interval arithmetics,…

WildMix Dataset and Spectro-Temporal Transformer Model for Monoaural Audio Source Separation. (arXiv:1911.09783v1 [cs.LG])

Monoaural audio source separation is a challenging research area in machine learning. In this area, a mixture containing multiple audio sources is given, and a model is expected to disentangle the mixture into isolated atomic sources. In this paper, we first introduce a challenging new dataset for monoaural source separation called WildMix. WildMix is designed…

Leveraging Sensing at the Infrastructure for mmWave Communication. (arXiv:1911.09796v1 [cs.IT])

Vehicle-to-everything (V2X) communication in the mmWave band is one way to achieve high data-rates for applications like infotainment, cooperative perception, and augmented reality assisted driving etc. MmWave communication relies on large antennas arrays, and configuring these arrays poses high training overhead. In this article, we motivate the use of infrastructure mounted sensors (which will be…

Incentivizing efficient use of shared infrastructure: Optimal tolls in congestion games. (arXiv:1911.09806v1 [cs.GT])

Throughout modern society, human users interact with large-scale engineered systems, e.g., road-traffic networks, electric power grids, wireless communication networks. As the performance of such systems greatly depends on the decisions made by the individual users – often leading to undesirable system behaviour – a natural question arises: How can we design incentives to promote efficient…

Multi-Objective Multi-Agent Planning for Jointly Discovering and Tracking Mobile Object. (arXiv:1911.09807v1 [cs.MA])

We consider the challenging problem of online planning for a team of agents to autonomously search and track a time-varying number of mobile objects under the practical constraint of detection range limited onboard sensors. A standard POMDP with a value function that either encourages discovery or accurate tracking of mobile objects is inadequate to simultaneously…

2SDR: Applying Kronecker Envelope PCA to denoise Cryo-EM Images. (arXiv:1911.09816v1 [eess.IV])

Principal component analysis (PCA) is arguably the most widely used dimension reduction method for vector type data. When applied to image data, PCA demands the images to be portrayed as vectors. The resulting computation is heavy because it will solve an eigenvalue problem of a huge covariance matrix due to the vectorization step. To mitigate…

Robust Learning-based Predictive Control for Constrained Nonlinear Systems. (arXiv:1911.09827v1 [eess.SY])

The integration of machine learning methods and Model Predictive Control (MPC) has received increasing attention in recent years. In general, learning-based predictive control (LPC) is promising to build data-driven models and solve the online optimization problem with lower computational costs. However, the robustness of LPC is difficult to be guaranteed since there will be uncertainties…

Identify the cells’ nuclei based on the deep learning neural network. (arXiv:1911.09830v1 [cs.CV])

Identify the cells’ nuclei is the important point for most medical analyses. To assist doctors finding the accurate cell’ nuclei location automatically is highly demanded in the clinical practice. Recently, fully convolutional neural network (FCNs) serve as the back-bone in many image segmentation, like liver and tumer segmentation in medical field, human body block in…