Unsupervised intra-lingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to estimate the transcription of the adaptation data. This paper first presents an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for such supplementary acoustic models. This is achieved by defining a mapping between HMM-based synthesis models and ASR-style models, via a two-pass decision tree construction process. Second, it is shown that this mapping also enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data. Third, this paper demonstrates how this technique lends itself to the task of unsupervised cross-lingual adaptation of HMM-based speech synthesis models, and explains the advantages of such an approach. Finally, listener evaluations reveal that the proposed unsupervised adaptation methods deliver performance approaching that of supervised adaptation.

Shortening the decision distance: Selecting decision aids for improved technology investment performance

Deciding which technology to invest in is a recurring issue for technology managers, and the ability to successfully identify the right technology can be a make or break decision for a company. The effects of globalisation have made this issue even more imperative. Not only do companies have to be competitive by global standards but increasingly they have to source technological capabilities from overseas as well. Technology managers already have a variety of decision aids to draw upon, including valuation tools, for example DCF and real options; decision trees; and technology roadmapping. However little theory exists on when, where, why or even how to best apply particular decision aids. Rather than developing further techniques, this paper reviews the relevance and limitations of existing techniques. This is drawn from an on going research project which seeks to support technology managers in selecting and applying existing decision aids and potentially in the design of future decision aids. It is intended that through improving the selection of decision aids, decision performance can be increased, leading to more effective allocation of resources and hence competitive advantage. (c) 2006 PICMET.

Deliberation in the motor system: reflex gains track evolving evidence leading to a decision.

Both decision making and sensorimotor control require real-time processing of noisy information streams. Historically these processes were thought to operate sequentially: cognitive processing leads to a decision, and the outcome is passed to the motor system to be converted into action. Recently, it has been suggested that the decision process may provide a continuous flow of information to the motor system, allowing it to prepare in a graded fashion for the probable outcome. Such continuous flow is supported by electrophysiology in nonhuman primates. Here we provide direct evidence for the continuous flow of an evolving decision variable to the motor system in humans. Subjects viewed a dynamic random dot display and were asked to indicate their decision about direction by moving a handle to one of two targets. We probed the state of the motor system by perturbing the arm at random times during decision formation. Reflex gains were modulated by the strength and duration of motion, reflecting the accumulated evidence in support of the evolving decision. The magnitude and variance of these gains tracked a decision variable that explained the subject's decision accuracy. The findings support a continuous process linking the evolving computations associated with decision making and sensorimotor control.

Motor control is decision-making.

Motor behavior may be viewed as a problem of maximizing the utility of movement outcome in the face of sensory, motor and task uncertainty. Viewed in this way, and allowing for the availability of prior knowledge in the form of a probability distribution over possible states of the world, the choice of a movement plan and strategy for motor control becomes an application of statistical decision theory. This point of view has proven successful in recent years in accounting for movement under risk, inferring the loss function used in motor tasks, and explaining motor behavior in a wide variety of circumstances.

Paradoxical evidence integration in rapid decision processes

Decisions about noisy stimuli require evidence integration over time. Traditionally, evidence integration and decision making are described as a one-stage process: a decision is made when evidence for the presence of a stimulus crosses a threshold. Here, we show that one-stage models cannot explain psychophysical experiments on feature fusion, where two visual stimuli are presented in rapid succession. Paradoxically, the second stimulus biases decisions more strongly than the first one, contrary to predictions of one-stage models and intuition. We present a two-stage model where sensory information is integrated and buffered before it is fed into a drift diffusion process. The model is tested in a series of psychophysical experiments and explains both accuracy and reaction time distributions. © 2012 Rüter et al.

Partially Observable Markov Decision Processes with continuous observations for dialogue management

This work shows how a dialogue model can be represented as a Partially Observable Markov Decision Process (POMDP) with observations composed of a discrete and continuous component. The continuous component enables the model to directly incorporate a confidence score for automated planning. Using a testbed simulated dialogue management problem, we show how recent optimization techniques are able to find a policy for this continuous POMDP which outperforms a traditional MDP approach. Further, we present a method for automatically improving handcrafted dialogue managers by incorporating POMDP belief state monitoring, including confidence score information. Experiments on the testbed system show significant improvements for several example handcrafted dialogue managers across a range of operating conditions.

Making a shallow network deep: Conversion of a boosting classifier into a decision tree by boolean optimisation

This paper presents a novel way to speed up the evaluation time of a boosting classifier. We make a shallow (flat) network deep (hierarchical) by growing a tree from decision regions of a given boosting classifier. The tree provides many short paths for speeding up while preserving the reasonably smooth decision regions of the boosting classifier for good generalisation. For converting a boosting classifier into a decision tree, we formulate a Boolean optimization problem, which has been previously studied for circuit design but limited to a small number of binary variables. In this work, a novel optimisation method is proposed for, firstly, several tens of variables i.e. weak-learners of a boosting classifier, and then any larger number of weak-learners by using a two-stage cascade. Experiments on the synthetic and face image data sets show that the obtained tree achieves a significant speed up both over a standard boosting classifier and the Fast-exit-a previously described method for speeding-up boosting classification, at the same accuracy. The proposed method as a general meta-algorithm is also useful for a boosting cascade, where it speeds up individual stage classifiers by different gains. The proposed method is further demonstrated for fast-moving object tracking and segmentation problems. © 2011 Springer Science+Business Media, LLC.

Proposal of a method to clarify and enhance decision-making at the front-end of innovation

Decision-making at the front-end of innovation is critical for the success of companies. This paper presents a simple visual method, called DMCA (Decision-Making Criteria Assessment), which was created to clarify and improve decision-making at the front-end of innovation. The method maps the uncertainty of project information and importance of decision criteria, compiling a measure that indicates whether the decision is highly uncertain, what information interferes with it, and what criteria are actually being considered. The DMCA method was tested in two projects that faced decision-making issues, and the results confirm the benefits of using this method in decision-making at the front-end. © 2012 IEEE.

The Silent Period of Evidence Integration in Fast Decision Making

In a typical experiment on decision making, one out of two possible stimuli is displayed and observers decide which one was presented. Recently, Stanford and colleagues (2010) introduced a new variant of this classical one-stimulus presentation paradigm to investigate the speed of decision making. They found evidence for "perceptual decision making in less than 30 ms". Here, we extended this one-stimulus compelled-response paradigm to a two-stimulus compelled-response paradigm in which a vernier was followed immediately by a second vernier with opposite offset direction. The two verniers and their offsets fuse. Only one vernier is perceived. When observers are asked to indicate the offset direction of the fused vernier, the offset of the second vernier dominates perception. Even for long vernier durations, the second vernier dominates decisions indicating that decision making can take substantial time. In accordance with previous studies, we suggest that our results are best explained with a two-stage model of decision making where a leaky evidence integration stage precedes a race-to-threshold process. © 2013 Rüter et al.