Acoustic model adaptation can mitigate the degradation in recognition accuracy caused by speaker or environment mismatch. While there are many methods for speaker or environment adaptation, far less attention has been focused on methods that compensate for both simultaneously. We recently proposed an algorithm called factored adaptation which jointly estimates speaker and environment transforms...

Sensorimotor adaptation ensures movement accuracy despite continuously changing environment and body. Adaptation of saccadic eye movements is a classical model of sensorimotor adaptation. Beside the well-established role of the brainstem-cerebellum in the adaptation of reactive saccades (RSs), the cerebral cortex has been suggested to be involved in the adaptation of voluntary saccades (VSs). H...

Statistical speech recognition using continuousdensity hidden Markov models (CDHMMs) has yielded many practical applications. However, in general, mismatches between the training data and input data significantly degrade recognition accuracy. Various acoustic model adaptation techniques using a few input utterances have been employed to overcome this problem. In this article, we survey these ad...

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...

An active learning approach is proposed to automatically analyze speech recognition tasks and select particularly useful adaptation data. In this approach, the distribution of task data is first estimated, which is a combination of two distributions based on N-best recognition results and low confidence data. After that, a subset of adaptation data is selected in two stages using a greedy algor...

A signal-separation front-end based on adaptive decorrelation ltering (ADF) was integrated with an HMM based speaker independent continuous speech recognition system for co-channel speech recognition. The ADF is improved by addressing the adaptation gain for system stability and e ciency: an upper bound of adaptation rate is derived for system stability, and an accelerated sequence of adaptatio...

The accuracy of saccadic eye movements is maintained by saccadic adaptation. Post-saccadic visual feedback about the error between the target position and the saccade endpoint is crucial to the adaptive process. The present experiments examine the adaptation of saccades that select a new target object (between-object saccades) and that of saccades that would not aim for a selected target but ex...

We provide a short overview of Importance Sampling – a popular sampling tool used for Monte Carlo computing. We discuss its mathematical foundation and properties that determine its accuracy in Monte Carlo approximations. We review the fundamental developments in designing efficient IS for practical use. This includes parametric approximation with optimization based adaptation, sequential sampl...

Spike-frequency adaptation is a common feature of neural dynamics. Here we present a low-dimensional phenomenological model whose parameters can be easily determined from experimental data. We test the model on intracellular recordings from auditory receptor neurons of locusts and demonstrate that the temporal variation of discharge rate is predicted with high accuracy. We relate the model to b...

Adaptive processes are crucial in maintaining the accuracy of body movements and rely on error storage and processing mechanisms. Although classically studied with adaptation paradigms, evidence of these ongoing error-correction mechanisms should also be detectable in other movements. Despite this connection, current adaptation models are challenged when forecasting adaptation ability with meas...