Gone in 0.6 seconds: the encoding of motor memories depends on recent sensorimotor states.

Real-world tasks often require movements that depend on a previous action or on changes in the state of the world. Here we investigate whether motor memories encode the current action in a manner that depends on previous sensorimotor states. Human subjects performed trials in which they made movements in a randomly selected clockwise or counterclockwise velocity-dependent curl force field. Movements during this adaptation phase were preceded by a contextual phase that determined which of the two fields would be experienced on any given trial. As expected from previous research, when static visual cues were presented in the contextual phase, strong interference (resulting in an inability to learn either field) was observed. In contrast, when the contextual phase involved subjects making a movement that was continuous with the adaptation-phase movement, a substantial reduction in interference was seen. As the time between the contextual and adaptation movement increased, so did the interference, reaching a level similar to that seen for static visual cues for delays >600 ms. This contextual effect generalized to purely visual motion, active movement without vision, passive movement, and isometric force generation. Our results show that sensorimotor states that differ in their recent temporal history can engage distinct representations in motor memory, but this effect decays progressively over time and is abolished by ∼600 ms. This suggests that motor memories are encoded not simply as a mapping from current state to motor command but are encoded in terms of the recent history of sensorimotor states.

Improving LVCSR system combination using neural network language model cross adaptation

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. The standard approach involves only cross adapting acoustic models. To fully exploit the complimentary features among sub-systems, language model (LM) cross adaptation techniques can be used. Previous research on multi-level n-gram LM cross adaptation is extended to further include the cross adaptation of neural network LMs in this paper. Using this improved LM cross adaptation framework, significant error rate gains of 4.0%-7.1% relative were obtained over acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. Copyright © 2011 ISCA.

Integrated online speaker clustering and adaptation

For many applications, it is necessary to produce speech transcriptions in a causal fashion. To produce high quality transcripts, speaker adaptation is often used. This requires online speaker clustering and incremental adaptation techniques to be developed. This paper presents an integrated approach to online speaker clustering and adaptation which allows efficient clustering of speakers using the same accumulated statistics that are normally used for adaptation. Using a consistent criterion for both clustering and adaptation should yield gains for both stages. The proposed approach is evaluated on a meetings transcription task using audio from multiple distant microphones. Consistent gains over standard clustering and adaptation were obtained. Copyright © 2011 ISCA.

Real-time block flow tracking of atrial septal defect motion in 4D cardiac ultrasound

Real-time cardiac ultrasound allows monitoring the heart motion during intracardiac beating heart procedures. Our application assists atrial septal defect (ASD) closure techniques using real-time 3D ultrasound guidance. One major image processing challenge is the processing of information at high frame rate. We present an optimized block flow technique, which combines the probability-based velocity computation for an entire block with template matching. We propose adapted similarity constraints both from frame to frame, to conserve energy, and globally, to minimize errors. We show tracking results on eight in-vivo 4D datasets acquired from porcine beating-heart procedures. Computing velocity at the block level with an optimized scheme, our technique tracks ASD motion at 41 frames/s. We analyze the errors of motion estimation and retrieve the cardiac cycle in ungated images. © 2007 IEEE.

Use of contexts in language model interpolation and adaptation

Language models (LMs) are often constructed by building multiple individual component models that are combined using context independent interpolation weights. By tuning these weights, using either perplexity or discriminative approaches, it is possible to adapt LMs to a particular task. This paper investigates the use of context dependent weighting in both interpolation and test-time adaptation of language models. Depending on the previous word contexts, a discrete history weighting function is used to adjust the contribution from each component model. As this dramatically increases the number of parameters to estimate, robust weight estimation schemes are required. Several approaches are described in this paper. The first approach is based on MAP estimation where interpolation weights of lower order contexts are used as smoothing priors. The second approach uses training data to ensure robust estimation of LM interpolation weights. This can also serve as a smoothing prior for MAP adaptation. A normalized perplexity metric is proposed to handle the bias of the standard perplexity criterion to corpus size. A range of schemes to combine weight information obtained from training data and test data hypotheses are also proposed to improve robustness during context dependent LM adaptation. In addition, a minimum Bayes' risk (MBR) based discriminative training scheme is also proposed. An efficient weighted finite state transducer (WFST) decoding algorithm for context dependent interpolation is also presented. The proposed technique was evaluated using a state-of-the-art Mandarin Chinese broadcast speech transcription task. Character error rate (CER) reductions up to 7.3 relative were obtained as well as consistent perplexity improvements. © 2012 Elsevier Ltd. All rights reserved.

Real-time marker prediction and CoR estimation in optical motion capture

Optical motion capture systems suffer from marker occlusions resulting in loss of useful information. This paper addresses the problem of real-time joint localisation of legged skeletons in the presence of such missing data. The data is assumed to be labelled 3d marker positions from a motion capture system. An integrated framework is presented which predicts the occluded marker positions using a Variable Turn Model within an Unscented Kalman filter. Inferred information from neighbouring markers is used as observation states; these constraints are efficient, simple, and real-time implementable. This work also takes advantage of the common case that missing markers are still visible to a single camera, by combining predictions with under-determined positions, resulting in more accurate predictions. An Inverse Kinematics technique is then applied ensuring that the bone lengths remain constant over time; the system can thereby maintain a continuous data-flow. The marker and Centre of Rotation (CoR) positions can be calculated with high accuracy even in cases where markers are occluded for a long period of time. Our methodology is tested against some of the most popular methods for marker prediction and the results confirm that our approach outperforms these methods in estimating both marker and CoR positions. © 2012 Springer-Verlag.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple sub-systems that may even be developed at different sites. Cross system adaptation, in which model adaptation is performed using the outputs from another sub-system, can be used as an alternative to hypothesis level combination schemes such as ROVER. Normally cross adaptation is only performed on the acoustic models. However, there are many other levels in LVCSR systems' modelling hierarchy where complimentary features may be exploited, for example, the sub-word and the word level, to further improve cross adaptation based system combination. It is thus interesting to also cross adapt language models (LMs) to capture these additional useful features. In this paper cross adaptation is applied to three forms of language models, a multi-level LM that models both syllable and word sequences, a word level neural network LM, and the linear combination of the two. Significant error rate reductions of 4.0-7.1% relative were obtained over ROVER and acoustic model only cross adaptation when combining a range of Chinese LVCSR sub-systems used in the 2010 and 2011 DARPA GALE evaluations. © 2012 Elsevier Ltd. All rights reserved.

Coordinated motion design on lie groups

The present paper proposes a unified geometric framework for coordinated motion on Lie groups. It first gives a general problem formulation and analyzes ensuing conditions for coordinated motion. Then, it introduces a precise method to design control laws in fully actuated and underactuated settings with simple integrator dynamics. It thereby shows that coordination can be studied in a systematic way once the Lie group geometry of the configuration space is well characterized. Applying the proposed general methodology to particular examples allows to retrieve control laws that have been proposed in the literature on intuitive grounds. A link with Brockett's double bracket flows is also made. The concepts are illustrated on SO(3), SE(2) and SE(3). © 2010 IEEE.

Stabilization of planar collective motion with limited communication

This paper proposes a design methodology to stabilize relative equilibria in a model of identical, steered particles moving in the plane at unit speed. Relative equilibria either correspond to parallel motion of all particles with fixed relative spacing or to circular motion of all particles around the same circle. Particles exchange relative information according to a communication graph that can be undirected or directed and time-invariant or time-varying. The emphasis of this paper is to show how previous results assuming all-to-all communication can be extended to a general communication framework. © 2008 IEEE.

Stabilization of symmetric formations to motion around convex loops

We provide a cooperative control algorithm to stabilize symmetric formations to motion around closed curves suitable for mobile sensor networks. This work extends previous results for stabilization of symmetric circular formations. We study a planar particle model with decentralized steering control subject to limited communication. Because of their unique spectral properties, the Laplacian matrices of circulant graphs play a key role. We illustrate the result for a skewed superellipse, which is a type of curve that includes circles, ellipses, and rounded parallelograms. © 2007 Elsevier B.V. All rights reserved.

Alternating spatial patterns for coordinated group motion

Motivated by recent observations of fish schools, we study coordinated group motion for individuals with oscillatory speed. Neighbors that have speed oscillations with common frequency, amplitude and average but different phases, move together in alternating spatial patterns, taking turns being towards the front, sides and back of the group. We propose a model and control laws to investigate the connections between these spatial dynamics, communication when sensing is range or direction limited, and convergence of coordinated group motions. ©2007 IEEE.