Recent advancements in neural end-to-end TTS models have shown high-quality, natural synthesized speech in a conventional sentence-based TTS. However, it is still challenging to reproduce similar high quality when a whole paragraph is considered in TTS, where a large amount of contextual information needs to be considered in building a paragraph-based TTS model. To alleviate the difficulty in training, we propose to model linguistic and prosodic information by considering cross-sentence, embedded structure in training. Three sub-modules, including linguistics-aware, prosody-aware and sentence-position networks, are trained together with a modified Tacotron2. Specifically, to learn the information embedded in a paragraph and the relations among the corresponding component sentences, we utilize linguistics-aware and prosody-aware networks. The information in a paragraph is captured by encoders and the inter-sentence information in a paragraph is learned with multi-head attention mechanisms. The relative sentence position in a paragraph is explicitly exploited by a sentence-position network. Trained on a storytelling audio-book corpus (4.08 hours), recorded by a female Mandarin Chinese speaker, the proposed TTS model demonstrates that it can produce rather natural and good-quality speech paragraph-wise. The cross-sentence contextual information, such as break and prosodic variations between consecutive sentences, can be better predicted and rendered than the sentence-based model. Tested on paragraph texts, of which the lengths are similar to, longer than, or much longer than the typical paragraph length of the training data, the TTS speech produced by the new model is consistently preferred over the sentence-based model in subjective tests and confirmed in objective measures.
In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition. To tackle the domain-shift which exists under the UDA setting, we first exploited a recent Domain Generalization (DG) technique, called Relative Norm Alignment (RNA). Secondly, we extended this approach to work on unlabelled target data, enabling a simpler adaptation of the model to the target distribution in an unsupervised fashion. To this purpose, we included in our framework UDA algorithms, such as multi-level adversarial alignment and attentive entropy. By analyzing the challenge setting, we notice the presence of a secondary concurrence shift in the data, which is usually called environmental bias. It is caused by the existence of different environments, i.e., kitchens. To deal with these two shifts (environmental and temporal), we extended our system to perform Multi-Source Multi-Target Domain Adaptation. Finally, we employed distinct models in our final proposal to leverage the potential of popular video architectures, and we introduced two more losses for the ensemble adaptation. Our submission (entry 'plnet') is visible on the leaderboard and ranked in 2nd position for 'verb', and in 3rd position for both 'noun' and 'action'.
Collaborative filtering problems are commonly solved based on matrix completion techniques which recover the missing values of user-item interaction matrices. In a matrix, the rating position specifically represents the user given and the item rated. Previous matrix completion techniques tend to neglect the position of each element (user, item and ratings) in the matrix but mainly focus on semantic similarity between users and items to predict the missing value in a matrix. This paper proposes a novel position-enhanced user/item representation training model for recommendation, SUPER-Rec. We first capture the rating position in the matrix using the relative positional rating encoding and store the position-enhanced rating information and its user-item relationship to the fixed dimension of embedding that is not affected by the matrix size. Then, we apply the trained position-enhanced user and item representations to the simplest traditional machine learning models to highlight the pure novelty of our representation learning model. We contribute the first formal introduction and quantitative analysis of position-enhanced item representation in the recommendation domain and produce a principled discussion about our SUPER-Rec to the outperformed performance of typical collaborative filtering recommendation tasks with both explicit and implicit feedback.
In this paper, we argue that recommendation systems are in a unique position to propagate dangerous and cruel behaviors to people with mental illnesses.
We present DIY-IPS - Do It Yourself - Indoor Positioning System, an open-source real-time indoor positioning mobile application. DIY-IPS detects users' indoor position by employing dual-band RSSI fingerprinting of available WiFi access points. The app can be used, without additional infrastructural costs, to detect users' indoor positions in real time. We published our app as an open source to save other researchers time recreating it. The app enables researchers/users to (1) collect indoor positioning datasets with a ground truth label, (2) customize the app for higher accuracy or other research purposes (3) test the accuracy of modified methods by live testing with ground truth. We ran preliminary experiments to demonstrate the effectiveness of the app.
Precise and accurate localization in outdoor and indoor environments is a challenging problem that currently constitutes a significant limitation for several practical applications. Ultra-wideband (UWB) localization technology represents a valuable low-cost solution to the problem. However, non-line-of-sight (NLOS) conditions and complexity of the specific radio environment can easily introduce a positive bias in the ranging measurement, resulting in highly inaccurate and unsatisfactory position estimation. In the light of this, we leverage the latest advancement in deep neural network optimization techniques and their implementation on ultra-low-power microcontrollers to introduce an effective range error mitigation solution that provides corrections in either NLOS or LOS conditions with a few mW of power. Our extensive experimentation endorses the advantages and improvements of our low-cost and power-efficient methodology.
The last several years have brought a growing body of work on ensuring that recommender systems are in some sense consumer-fair -- that is, they provide comparable quality of service, accuracy of representation, and other effects to their users. However, there are many different strategies to make systems more fair and a range of intervention points. In this position paper, we build on ongoing work to highlight the need for researchers and practitioners to attend to the details of their application, users, and the fairness objective they aim to achieve, and adopt interventions that are appropriate to the situation. We argue that consumer fairness should be a creative endeavor flowing from the particularities of the specific problem to be solved.
This paper describes and discusses our vision to develop and reason about best practices and novel ways of curating data-centric geosciences knowledge (data, experiments, models, methods, conclusions, and interpretations). This knowledge is produced from applying statistical modelling, Machine Learning, and modern data analytics methods on geo-data collections. The problems address open methodological questions in model building, models' assessment, prediction, and forecasting workflows.
Purpose The purpose of this paper is to explore which structures of academic articles referees would pay more attention to, what specific content referees focus on, and whether the distribution of PRC is related to the citations. Design/methodology/approach Firstly, utilizing the feature words of section title and hierarchical attention network model (HAN) to identify the academic article structures. Secondly, analyzing the distribution of PRC in different structures according to the position information extracted by rules in PRC. Thirdly, analyzing the distribution of feature words of PRC extracted by the Chi-square test and TF-IDF in different structures. Finally, four correlation analysis methods are used to analyze whether the distribution of PRC in different structures is correlated to the citations. Findings The count of PRC distributed in Materials and Methods and Results section is significantly more than that in the structure of Introduction and Discussion, indicating that referees pay more attention to the Material and Methods and Results. The distribution of feature words of PRC in different structures is obviously different, which can reflect the content of referees' concern. There is no correlation between the distribution of PRC in different structures and the citations. Research limitations/implications Due to the differences in the way referees write peer review reports, the rules used to extract position information cannot cover all PRC. Originality/value The paper finds a pattern in the distribution of PRC in different academic article structures proving the long-term empirical understanding. It also provides insight into academic article writing: researchers should ensure the scientificity of methods and the reliability of results when writing academic article to obtain a high degree of recognition from referees.
We introduce a novel technique and an associated high resolution dataset that aims to precisely evaluate wireless signal based indoor positioning algorithms. The technique implements an augmented reality (AR) based positioning system that is used to annotate the wireless signal parameter data samples with high precision position data. We track the position of a practical and low cost navigable setup of cameras and a Bluetooth Low Energy (BLE) beacon in an area decorated with AR markers. We maximize the performance of the AR-based localization by using a redundant number of markers. Video streams captured by the cameras are subjected to a series of marker recognition, subset selection and filtering operations to yield highly precise pose estimations. Our results show that we can reduce the positional error of the AR localization system to a rate under 0.05 meters. The position data are then used to annotate the BLE data that are captured simultaneously by the sensors stationed in the environment, hence, constructing a wireless signal data set with the ground truth, which allows a wireless signal based localization system to be evaluated accurately.
With the rise of increasingly complex autonomous systems powered by black box AI models, there is a growing need for Run Time Assurance (RTA) systems that provide online safety filtering to untrusted primary controller output. Currently, research in RTA tends to be ad hoc and inflexible, diminishing collaboration and the pace of innovation. The Safe Autonomy Run Time Assurance Framework presented in this paper provides a standardized interface for RTA modules and a set of universal implementations of constraint-based RTA capable of providing safety assurance given arbitrary dynamical systems and constraints. Built around JAX, this framework leverages automatic differentiation to populate advanced optimization based RTA methods minimizing user effort and error. To validate the feasibility of this framework, a simulation of a multi-agent spacecraft inspection problem is shown with safety constraints on position and velocity.
Position detection of hydraulic cylinder pistons is crucial for numerous industrial automation applications. A typical traditional method is to excite electromagnetic waves in the cylinder structure and analytically solve the piston position based on the scattering parameters measured by a sensor. The core of this approach is a physical model that outlines the relationship between the measured scattering parameters and the targeted piston position. However, this physical model has shortcomings in accuracy and adaptability, especially in extreme conditions. To address these limitations, we propose machine learning and deep learning-based methods to learn the relationship directly in a data-driven manner. As a result, all deep learning models in this paper consistently outperform the physical one by a large margin. We further deliberate on the choice of models based on domain knowledge and provide in-depth analyses combining model performance with real-world physical characteristics. Specifically, we use Convolutional Neural Network (CNN) to discover local interactions of input among adjacent frequencies, apply Complex-Valued Neural Network (CVNN) to exploit the complex-valued nature of electromagnetic scattering parameters, and introduce a novel technique named Frequency Encoding to add weighted frequency information to the model input. The combination of these techniques results in our best-performing model, a complex-valued CNN with Frequency Encoding, which exhibits substantial improvement in accuracy with an error reduction of 1/12 compared to the traditional physical model.
Learning to detect objects, such as humans, in imagery captured by an unmanned aerial vehicle (UAV) usually suffers from tremendous variations caused by the UAV's position towards the objects. In addition, existing UAV-based benchmark datasets do not provide adequate dataset metadata, which is essential for precise model diagnosis and learning features invariant to those variations. In this paper, we introduce Archangel, the first UAV-based object detection dataset composed of real and synthetic subsets captured with similar imagining conditions and UAV position and object pose metadata. A series of experiments are carefully designed with a state-of-the-art object detector to demonstrate the benefits of leveraging the metadata during model evaluation. Moreover, several crucial insights involving both real and synthetic data during model optimization are presented. In the end, we discuss the advantages, limitations, and future directions regarding Archangel to highlight its distinct value for the broader machine learning community.
In this work, we present a novel way of computing IPS using a position-bias model for deterministic logging policies. This technique significantly widens the policies on which OPE can be used. We validate this technique using two different experiments on industry-scale data. The OPE results are clearly strongly correlated with the online results, with some constant bias. The estimator requires the examination model to be a reasonably accurate approximation of real user behaviour.
Millimeter wave (mmWave) radar sensors are emerging as valid alternatives to cameras for the pervasive contactless monitoring of people in indoor spaces. However, commercial mmWave radars feature a limited range (up to $6$-$8$ m) and are subject to occlusion, which may constitute a significant drawback in large, crowded rooms characterized by a challenging multipath environment. Thus, covering large indoor spaces requires multiple radars with known relative position and orientation and algorithms to combine their outputs. In this work, we present ORACLE, an autonomous system that (i) integrates automatic relative position and orientation estimation from multiple radar devices by exploiting the trajectories of people moving freely in the radars' common fields of view, and (ii) fuses the tracking information from multiple radars to obtain a unified tracking among all sensors. Our implementation and experimental evaluation of ORACLE results in median errors of $0.12$ m and $0.03^\circ$ for radars location and orientation estimates, respectively. Fused tracking improves the mean target tracking accuracy by $27\%$, and the mean tracking error is $23$ cm in the most challenging case of $3$ moving targets. Finally, ORACLE does not show significant performance reduction when the fusion rate is reduced to up to 1/5 of the frame rate of the single radar sensors, thus being amenable to a lightweight implementation on a resource-constrained fusion center.
This paper proposes a new method for RTK post-processing. Different from the traditional forward-backward Kalman filter, in our method, the whole system equation is built on a graphical state space model and solved by factor graph optimization. The position solution provided by the forward Kalman filter is used as the linearization points of the graphical state space model. Constant variables, such as double-difference ambiguity, will exist as constants in the graphical state space model, not as time-series variables. It is shown by experiment results that factor graph optimization with a graphical state space model is more effective than Kalman filter with a traditional discrete-time state space model for RTK post-processing problem.
This paper describes a framework for the object-goal navigation task, which requires a robot to find and move to the closest instance of a target object class from a random starting position. The framework uses a history of robot trajectories to learn a Spatial Relational Graph (SRG) and Graph Convolutional Network (GCN)-based embeddings for the likelihood of proximity of different semantically-labeled regions and the occurrence of different object classes in these regions. To locate a target object instance during evaluation, the robot uses Bayesian inference and the SRG to estimate the visible regions, and uses the learned GCN embeddings to rank visible regions and select the region to explore next.
AI engines utilizing deep learning neural networks provide excellent tools for analyzing traditional board games. Here we are interested in gaining new insights into the ancient game of Go. For that purpose, we need to define new numerical measures based on the raw output of the engines. In this paper, we develop a numerical tool for automated move-by-move performance evaluation in a context-sensitive manner and for recognizing game features. We measure the urgency of a move by the cost of passing, which is the score value difference between the current configuration of stones and after a hypothetical pass in the same board position. Here we investigate the properties of this measure and describe some applications.
In this paper, we revisit the use of spectrograms in neural networks, by making the window length a continuous parameter optimizable by gradient descent instead of an empirically tuned integer-valued hyperparameter. The contribution is mostly theoretical at this point, but plugging the modified STFT into any existing neural network is straightforward. We first define a differentiable version of the STFT in the case where local bins centers are fixed and independent of the window length parameter. We then discuss the more difficult case where the window length affects the position and number of bins. We illustrate the benefits of this new tool on an estimation and a classification problems, showing it can be of interest not only to neural networks but to any STFT-based signal processing algorithm.
Existing top-performance 3D object detectors typically rely on the multi-modal fusion strategy. This design is however fundamentally restricted due to overlooking the modality-specific useful information and finally hampering the model performance. To address this limitation, in this work we introduce a novel modality interaction strategy where individual per-modality representations are learned and maintained throughout for enabling their unique characteristics to be exploited during object detection. To realize this proposed strategy, we design a DeepInteraction architecture characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Experiments on the large-scale nuScenes dataset show that our proposed method surpasses all prior arts often by a large margin. Crucially, our method is ranked at the first position at the highly competitive nuScenes object detection leaderboard.