A method is proposed to improve any temporal pattern recognition system by time warping each pattern before presentation to the recognition system. The time warping function for a pattern is generated by repeated local application of a neural network to sections of the pattern. The output of this neural network is the slope of the warping function, and the internal weight parameters are trained...

Warping can be used to reduce interindividual structural variations of 3D image datasets of brains by generating a standard brain and subsequent matching of individual datasets to this reference system. Point-based warping uses structural information (landmarks) to construct the spatial correspondence between the datasets. For this we compare the performance of three landmark detection algorith...

Vocal tract length normalization is an important feature normalization technique that can be used to perform speaker adaptation when very little adaptation data is available. It was shown earlier that VTLN can be applied to statistical speech synthesis and was shown to give additive improvements to CMLLR. This paper presents an EM optimization for estimating more accurate warping factors. The E...

Vocal tract length normalization is an important feature normalization technique that can be used to perform speaker adaptation when very little adaptation data is available. It was shown earlier that VTLN can be applied to statistical speech synthesis and was shown to give additive improvements to CMLLR. This paper presents an EM optimization for estimating more accurate warping factors. The E...

In this paper! we present improvements over the original scalecepstrum proposed in [ 11. The scalecepstrum was motivated by a desire to normalize the first-order effects of differences in vocal-tract lengths for a given vowel. Our subsequent work [2] has shown that a more appropriate frequency-warping than the log-warping used in [l] is necessary to account for the frequency dependency of the s...

Retrieval of similar heart sounds from a sound database has applications in physician training, diagnostic screening, and decision support. In this paper, we exploit a visual rendering of heart sounds and model the morphological variations of audio envelopes through a constrained non-rigid translation transform. Similar heart sounds are then retrieved by recovering the corresponding alignment t...

We outline our seamless tiled display system for interactive 3D graphics applications that is low-cost, easy to calibrate, scalable, and portable. Our system achieves geometric alignment in software by pre-warping the 3D space in contrast with the current systems that usually achieve this by 2D image pre-warping. Our system accomplishes this through real-time image capture from a digital camcor...

In this paper, the effectiveness of piecewise linear two-dimensional warping, a dynamic programming-based elastic image matching technique, in handwritten character recognition is investigated. The present technique is capable of providing compensation for most variations in character patterns while its computation remains tractable. The superiority of the present technique over several convent...

In this paper, a time warping algorithm is implemented and its performance is evaluated in the context of Adaptive MultiRate (AMR) wideband (WB) and narrowband (NB) speech coders. The aim of time warping is to achieve bit savings in transmission of pitch information with no significant quality degradations. In the case of AMR-NB and AMR-WB speech coders, these bit savings are 0.65-1.15 kbit/s d...

INTRODUCTION: Respiratory motion is a major challenge for 3D abdominal MRI. Respiratory navigator gating is commonly used to compensate for motion, but leads to low scan efficiency. Recently, a free-breathing motion compensated technique was proposed that estimates 3D non-rigid motion from undersampled reconstructed images. This technique compensates motion by warping the undersampled images to...