Statistical parametric speech synthesis based on speaker and language factorization

An increasingly common scenario in building speech synthesis and recognition systems is training on inhomogeneous data. This paper proposes a new framework for estimating hidden Markov models on data containing both multiple speakers and multiple languages. The proposed framework, speaker and language factorization, attempts to factorize speaker-/language-specific characteristics in the data and then model them using separate transforms. Language-specific factors in the data are represented by transforms based on cluster mean interpolation with cluster-dependent decision trees. Acoustic variations caused by speaker characteristics are handled by transforms based on constrained maximum-likelihood linear regression. Experimental results on statistical parametric speech synthesis show that the proposed framework enables data from multiple speakers in different languages to be used to: train a synthesis system; synthesize speech in a language using speaker characteristics estimated in a different language; and adapt to a new language. © 2012 IEEE.

Phrase-based statistical language generation using graphical models and active learning

Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to inform the generation decision process. Both approaches rely on the existence of a handcrafted generator, which limits their scalability to new domains. This paper presents BAGEL, a statistical language generator which uses dynamic Bayesian networks to learn from semantically-aligned data produced by 42 untrained annotators. A human evaluation shows that BAGEL can generate natural and informative utterances from unseen inputs in the information presentation domain. Additionally, generation performance on sparse datasets is improved significantly by using certainty-based active learning, yielding ratings close to the human gold standard with a fraction of the data. © 2010 Association for Computational Linguistics.

Improving statistical machine translation by classifying and generalizing inflected verb forms

This paper introduces a rule-based classification of single-word and compound verbs into a statistical machine translation approach. By substituting verb forms by the lemma of their head verb, the data sparseness problem caused by highly-inflected languages can be successfully addressed. On the other hand, the information of seen verb forms can be used to generate new translations for unseen verb forms. Translation results for an English to Spanish task are reported, producing a significant performance improvement.

An ngram-based statistical machine translation decoder

In this paper we describe MARIE, an Ngram-based statistical machine translation decoder. It is implemented using a beam search strategy, with distortion (or reordering) capabilities. The underlying translation model is based on an Ngram approach, extended to introduce reordering at the phrase level. The search graph structure is designed to perform very accurate comparisons, what allows for a high level of pruning, improving the decoder efficiency. We report several techniques for efficiently prune out the search space. The combinatory explosion of the search space derived from the search graph structure is reduced by limiting the number of reorderings a given translation is allowed to perform, and also the maximum distance a word (or a phrase) is allowed to be reordered. We finally report translation accuracy results on three different translation tasks.

Phrase linguistic classification and generalization for improving statistical machine translation

In this paper a method to incorporate linguistic information regarding single-word and compound verbs is proposed, as a first step towards an SMT model based on linguistically-classified phrases. By substituting these verb structures by the base form of the head verb, we achieve a better statistical word alignment performance, and are able to better estimate the translation model and generalize to unseen verb forms during translation. Preliminary experiments for the English - Spanish language pair are performed, and future research lines are detailed. © 2005 Association for Computational Linguistics.

State-space inference and learning with Gaussian processes

State-space inference and learning with Gaussian processes (GPs) is an unsolved problem. We propose a new, general methodology for inference and learning in nonlinear state-space models that are described probabilistically by non-parametric GP models. We apply the expectation maximization algorithm to iterate between inference in the latent state-space and learning the parameters of the underlying GP dynamics model. Copyright 2010 by the authors.

Information theory, inference, and learning algorithms

Fun and exciting textbook on the mathematics underpinning the most dynamic areas of modern science and engineering.

Automated 3D Structure Inference of Civil Infrastructure Using a Stereo Camera Set

The commercial far-range (>10m) infrastructure spatial data collection methods are not completely automated. They need significant amount of manual post-processing work and in some cases, the equipment costs are significant. This paper presents a method that is the first step of a stereo videogrammetric framework and holds the promise to address these issues. Under this method, video streams are initially collected from a calibrated set of two video cameras. For each pair of simultaneous video frames, visual feature points are detected and their spatial coordinates are then computed. The result, in the form of a sparse 3D point cloud, is the basis for the next steps in the framework (i.e., camera motion estimation and dense 3D reconstruction). A set of data, collected from an ongoing infrastructure project, is used to show the merits of the method. Comparison with existing tools is also shown, to indicate the performance differences of the proposed method in the level of automation and the accuracy of results.

Linear gaussian computations for near-exact Bayesian Monte Carlo inference in skewed alpha-stable time series models

In this paper we study parameter estimation for time series with asymmetric α-stable innovations. The proposed methods use a Poisson sum series representation (PSSR) for the asymmetric α-stable noise to express the process in a conditionally Gaussian framework. That allows us to implement Bayesian parameter estimation using Markov chain Monte Carlo (MCMC) methods. We further enhance the series representation by introducing a novel approximation of the series residual terms in which we are able to characterise the mean and variance of the approximation. Simulations illustrate the proposed framework applied to linear time series, estimating the model parameter values and model order P for an autoregressive (AR(P)) model driven by asymmetric α-stable innovations. © 2012 IEEE.

Decomposing signals into a sum of amplitude and frequency modulated sinusoids using probabilistic inference

There are many methods for decomposing signals into a sum of amplitude and frequency modulated sinusoids. In this paper we take a new estimation based approach. Identifying the problem as ill-posed, we show how to regularize the solution by imposing soft constraints on the amplitude and phase variables of the sinusoids. Estimation proceeds using a version of Kalman smoothing. We evaluate the method on synthetic and natural, clean and noisy signals, showing that it outperforms previous decompositions, but at a higher computational cost. © 2012 IEEE.

A high-resolution atlas and statistical model of the human heart from multislice CT

Atlases and statistical models play important roles in the personalization and simulation of cardiac physiology. For the study of the heart, however, the construction of comprehensive atlases and spatio-temporal models is faced with a number of challenges, in particular the need to handle large and highly variable image datasets, the multi-region nature of the heart, and the presence of complex as well as small cardiovascular structures. In this paper, we present a detailed atlas and spatio-temporal statistical model of the human heart based on a large population of 3D+time multi-slice computed tomography sequences, and the framework for its construction. It uses spatial normalization based on nonrigid image registration to synthesize a population mean image and establish the spatial relationships between the mean and the subjects in the population. Temporal image registration is then applied to resolve each subject-specific cardiac motion and the resulting transformations are used to warp a surface mesh representation of the atlas to fit the images of the remaining cardiac phases in each subject. Subsequently, we demonstrate the construction of a spatio-temporal statistical model of shape such that the inter-subject and dynamic sources of variation are suitably separated. The framework is applied to a 3D+time data set of 138 subjects. The data is drawn from a variety of pathologies, which benefits its generalization to new subjects and physiological studies. The obtained level of detail and the extendability of the atlas present an advantage over most cardiac models published previously. © 1982-2012 IEEE.

Optimal inference of sameness.

Deciding whether a set of objects are the same or different is a cornerstone of perception and cognition. Surprisingly, no principled quantitative model of sameness judgment exists. We tested whether human sameness judgment under sensory noise can be modeled as a form of probabilistically optimal inference. An optimal observer would compare the reliability-weighted variance of the sensory measurements with a set size-dependent criterion. We conducted two experiments, in which we varied set size and individual stimulus reliabilities. We found that the optimal-observer model accurately describes human behavior, outperforms plausible alternatives in a rigorous model comparison, and accounts for three key findings in the animal cognition literature. Our results provide a normative footing for the study of sameness judgment and indicate that the notion of perception as near-optimal inference extends to abstract relations.