In this paper, we show how to accomodate a Bayesian variant of Rissanen’s MDL into on-line Bayesian adaptation to control both model structural complexity and parameterization complexity to best fit an available amount of adaptation data, the goal being minimization of resulting recognition error. An efficient bottom-up dynamic programming based pruning algorithm is developed for selecting mode...

In this paper, the problem of fast model adaptation for nonnative speakers is addressed from a perspective of model complexity selection. The key challenge lies in reliable complexity selection when only a small amount of adaptation data is available. A novel maximum expected likelihood (MEL) based technique is proposed to enable model complexity selection from using as little as one adaptation...

ACOUSTIC MODEL ADAPTATION FOR AUTOMATIC SPEECH RECOGNITION AND ANIMAL VOCALIZATION CLASSIFICATION Jidong Tao, B.Eng., M.S. Marquette University, 2009 Automatic speech recognition (ASR) converts human speech to readable text. Acoustic model adaptation, also called speaker adaptation, is one of the most promising techniques in ASR for improving recognition accuracy. Adaptation works by tuning a g...

Two models of statistical dependence between acoustic model parameters of a large vocabulary conversational speech recognition (LVCSR) system are investigated for the purpose of rapid speakerand environment-adaptation from a very small amount of speech: (i) a Gaussian multiscale process governed by a stochastic linear dynamical system on a tree, and (ii) a simple hierarchical treestructured pri...

Until now, error and conflict adaptation have been studied extensively using simple laboratory tasks. A common finding is that responses slow down after errors. According to the conflict monitoring theory, performance should also improve after an error. However, this is usually not observed. In this study, we investigated whether the characteristics of the experimental paradigms normally used c...

Recent advances in Machine Translation (MT) have brought forth a new paradigm for building NLP applications in low-resource scenarios. To build a sentiment classifier for a language with no labeled resources, one can translate labeled data from another language, then train a classifier on the translated text. This can be viewed as a domain adaptation problem, where labeled translations and test...

Speaker adaptation is an important issue in current speech recognition researches. Speaker clustering is one of the widely used methods in speaker adaptation. In this paper the effect of Linear Discriminant Analysis (LDA) on increasing the accuracy of some clustering methods such as k-means and Support Vector Machine (SVM) is demonstrated. The performance of this idea was examined on AURORA 2.0...

the length o ti time series with adaption period was proposed by Chen et al as one of the mechanisms in improving forecasting accuracy. First, second, third and fourth order fuzzy times series based on multi-period adaptation models were successfully tested with stock exchange indexes in Taiwan and Hong Kong. However feasibility of the fourth order model especially the effect of multi-period ad...

Two critical stages in case-based design are the retrieval of a suitable design and the adaptation of that design. When a new design problem is presented to the system, the retrieval stage locates a similar design solution that is reusable in the current context. During adaptation, retrieved designs are modified to meet the specific demands of the target problem. In this paper, we address both ...

We investigate fast and efficient adaptation algorithms for linear transversal feed-forward (FFE) and decision feedback (DFE) equalizers in intensity modulated optical communication systems with direct detection (IM/DD). First, we employ the well-known minimum mean square error (MMSE) adaptation criterion and give a benchmark with respect to minimal bit error rate (BER). We further take the lea...