ABSTRACT Most neural-network based speaker-adaptive acoustic models for speech synthesis can be categorized into either layer-based or input-code approaches. Although both approaches have their own pros and cons, most existing works on speaker adaptation focus on improving one or the other. In this paper, after we first systematically overview the common principles of neural-network based speaker-adaptive models, we show that these approaches can be represented in a unified framework and can be generalized further. More specifically, we introduce the use of scaling and bias codes as generalized means for speaker-adaptive transformation. By utilizing these codes, we can create a more efficient factorized speaker-adaptive model and capture advantages of both approaches while reducing their disadvantages. The experiments show that the proposed method can improve the performance of speaker adaptation compared with speaker adaptation based on the conventional input code. Index Terms -- speech synthesis, speaker adaptation, neural network, factorization, speaker code 1. INTRODUCTION Recent speaker-dependent speech synthesis systems can generate high-quality reading speech indistinguishable from natural human speech when their training data is recorded in a quality-controlled condition and have sufficient amount of data [1].

We consider Markov models of stochastic processes where the next-step conditional distribution is defined by a kernel density estimator (KDE), similar to Markov forecast densities and certain time-series bootstrap schemes. The KDE Markov models (KDE-MMs) we discuss are nonlinear, nonparametric, fully probabilistic representations of stationary processes, based on techniques with strong asymptotic consistency properties. The models generate new data by concatenating points from the training data sequences in a context-sensitive manner, together with some additive driving noise. We present novel EM-type maximum-likelihood algorithms for data-driven bandwidth selection in KDE-MMs. Additionally, we augment the KDE-MMs with a hidden state, yielding a new model class, KDE-HMMs. The added state variable captures non-Markovian long memory and signal structure (e.g., slow oscillations), complementing the short-range dependences described by the Markov process. The resulting joint Markov and hidden-Markov structure is appealing for modelling complex real-world processes such as speech signals. We present guaranteed-ascent EM-update equations for model parameters in the case of Gaussian kernels, as well as relaxed update formulas that greatly accelerate training in practice. Experiments demonstrate increased held-out set probability for KDE-HMMs on several challenging natural and synthetic data series, compared to traditional techniques such as autoregressive models, HMMs, and their combinations.

Generating versatile and appropriate synthetic speech requires control over the output expression separate from the spoken text. Important non-textual speech variation is seldom annotated, in which case output control must be learned in an unsupervised fashion. In this paper, we perform an in-depth study of methods for unsupervised learning of control in statistical speech synthesis. For example, we show that popular unsupervised training heuristics can be interpreted as variational inference in certain autoencoder models. We additionally connect these models to VQ-VAEs, another, recently-proposed class of deep variational autoencoders, which we show can be derived from a very similar mathematical argument. The implications of these new probabilistic interpretations are discussed. We illustrate the utility of the various approaches with an application to emotional speech synthesis, where the unsupervised methods for learning expression control (without access to emotional labels) are found to give results that in many aspects match or surpass the previous best supervised approach.

We study the problem of synthesizing a policy that maximizes the entropy of a Markov decision process (MDP) subject to a temporal logic constraint. Such a policy minimizes the predictability of the paths it generates, or dually, maximizes the continual exploration of different paths in an MDP while ensuring the satisfaction of a temporal logic specification. We first show that the maximum entropy of an MDP can be finite, infinite or unbounded. We provide necessary and sufficient conditions under which the maximum entropy of an MDP is finite, infinite or unbounded. We then present an algorithm to synthesize a policy that maximizes the entropy of an MDP. The proposed algorithm is based on a convex optimization problem and runs in time polynomial in the size of the MDP. We also show that maximizing the entropy of an MDP is equivalent to maximizing the entropy of the paths that reach a certain set of states in the MDP. Finally, we extend the algorithm to an MDP subject to a temporal logic specification. In numerical examples, we demonstrate the proposed method on different motion planning scenarios and illustrate that as the restrictions imposed on the paths by a specification increase, the maximum entropy decreases, which in turn, increases the predictability of paths.

Learning nonlinear dynamics from diffusion data is a challenging problem since the individuals observed may be different at different time points, generally following an aggregate behaviour. Existing work cannot handle the tasks well since they model such dynamics either directly on observations or enforce the availability of complete longitudinal individual-level trajectories. However, in most of the practical applications, these requirements are unrealistic: the evolving dynamics may be too complex to be modeled directly on observations, and individual-level trajectories may not be available due to technical limitations, experimental costs and/or privacy issues. To address these challenges, we formulate a model of diffusion dynamics as the {\em hidden stochastic process} via the introduction of hidden variables for flexibility, and learn the hidden dynamics directly on {\em aggregate observations} without any requirement for individual-level trajectories. We propose a dynamic generative model with Wasserstein distance for LEarninG dEep hidden Nonlinear Dynamics (LEGEND) and prove its theoretical guarantees as well. Experiments on a range of synthetic and real-world datasets illustrate that LEGEND has very strong performance compared to state-of-the-art baselines.

Latent truth discovery, LTD for short, refers to the problem of aggregating ltiple claims from various sources in order to estimate the plausibility of atements about entities. In the absence of a ground truth, this problem is highly challenging, when some sources provide conflicting claims and others no claims at all. In this work we provide an unsupervised stochastic inference procedure on top of a model that combines restricted Boltzmann machines with feed-forward neural networks to accurately infer the reliability of sources as well as the plausibility of statements about entities. In comparison to prior work our approach stands out (1) by allowing the incorporation of arbitrary features about sources and claims, (2) by generalizing from reliability per source towards a reliability function, and thus (3) enabling the estimation of source reliability even for sources that have provided no or very few claims, (4) by building on efficient and scalable stochastic inference algorithms, and (5) by outperforming the state-of-the-art by a considerable margin.

We present a method of endowing agents in an agent-based model (ABM) with sophisticated cognitive capabilities and a naturally tunable level of intelligence. Often, ABMs use random behavior or greedy algorithms for maximizing objectives (such as a predator always chasing after the closest prey). However, random behavior is too simplistic in many circumstances and greedy algorithms, as well as classic AI planning techniques, can be brittle in the context of the unpredictable and emergent situations in which agents may find themselves. Our method, called agent-centric Monte Carlo cognition (ACMCC), centers around using a separate agent-based model to represent the agents' cognition. This model is then used by the agents in the primary model to predict the outcomes of their actions, and thus guide their behavior. To that end, we have implemented our method in the NetLogo agent-based modeling platform, using the recently released LevelSpace extension, which we developed to allow NetLogo models to interact with other NetLogo models. As an illustrative example, we extend the Wolf Sheep Predation model (included with NetLogo) by using ACMCC to guide animal behavior, and analyze the impact on agent performance and model dynamics. We find that ACMCC provides a reliable and understandable method of controlling agent intelligence, and has a large impact on agent performance and model dynamics even at low settings.

Semantically understanding complex drivers' encountering behavior, wherein two or multiple vehicles are spatially close to each other, does potentially benefit autonomous car's decision-making design. This paper presents a framework of analyzing various encountering behaviors through decomposing driving encounter data into small building blocks, called driving primitives, using nonparametric Bayesian learning (NPBL) approaches, which offers a flexible way to gain an insight into the complex driving encounters without any prerequisite knowledge. The effectiveness of our proposed primitive-based framework is validated based on 976 naturalistic driving encounters, from which more than 4000 driving primitives are learned using NPBL - a sticky HDP-HMM, combined a hidden Markov model (HMM) with a hierarchical Dirichlet process (HDP). After that, a dynamic time warping method integrated with k-means clustering is then developed to cluster all these extracted driving primitives into groups. Experimental results find that there exist 20 kinds of driving primitives capable of representing the basic components of driving encounters in our database. This primitive-based analysis methodology potentially reveals underlying information of vehicle-vehicle encounters for self-driving applications.

Today's automated vehicles lack the ability to cooperate implicitly with others. This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in heterogeneous environments. Based on cooperative modeling of other agents and Decoupled-UCT (a variant of MCTS), the algorithm evaluates the state-action-values of each agent in a cooperative and decentralized manner, explicitly modeling the interdependence of actions between traffic participants. Macro-actions allow for temporal extension over multiple time steps and increase the effective search depth requiring fewer iterations to plan over longer horizons. Without predefined policies for macro-actions, the algorithm simultaneously learns policies over and within macro-actions. The proposed method is evaluated under several conflict scenarios, showing that the algorithm can achieve effective cooperative planning with learned macro-actions in heterogeneous environments.

Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has received immense interest in recent times and success manifests itself in the form of human-level performance on games like \textit{Go}. While RL is emerging as a practical component in real-life systems, most successes have been in Single Agent domains. This report will instead specifically focus on challenges that are unique to Multi-Agent Systems interacting in mixed cooperative and competitive environments. The report concludes with advances in the paradigm of training Multi-Agent Systems called \textit{Decentralized Actor, Centralized Critic}, based on an extension of MDPs called \textit{Decentralized Partially Observable MDP}s, which has seen a renewed interest lately.