This paper proposes a novel neural network architecture for phoneme-based speech recognition. The new architecture is composed of five time-warping sub-networks and an output layer which integrates the sub-networks. Each time-warping sub-network has a different time-warping function embedded between the input layer and the first hidden layer. A time-warping sub-network recognizes the input spee...

Many image-based rendering systems are based on three-dimensional image warping (3D Warping), which transforms pixels in reference image to destination view. However, the original 3D warping equation, proposed by McMillan and Bishop, is derived under one special coordinate system, making its inability of direct implementation on programmable graphics hardware. In this paper, we revisit the 3D w...

Warping (Franz et al., 1998b) and 2Dwarping (Möller, 2009) are effective visual homing methods which can be applied for navigation in topological maps. This paper presents several improvements of 2D-warping and introduces two novel “free” warping methods in the same framework. The free warping methods partially lift the assumption of the original warping method that all landmarks have the same ...

We present wavelet warping — a new class of forward 3D warping algorithms for image-based rendering. In wavelet warping most of the warping operation is performed in the wavelet domain, by operating on the coefficients of the wavelet transforms of the images and other matrices defined by the mapping. Operating in this fashion is often more efficient than performing the 3D warp in the standard m...

Warping, also known as Control Grid Interpolation, estimates intensities in the present frame through an interpolation of motion vectors { typically with bilinear interpolation. This paper presents a method for computing optimal interpolation parameters for warping prediction. Conventional bilinear warping, while mostly eeective, has been known to exhibit unreliable performance in certain situa...

We show a proof of principle for warping, a method to interpret the inner working of neural networks in the context of gene expression analysis. Warping is an efficient way to gain insight to the inner workings of neural nets and make them more interpretable. We demonstrate the ability of warping to recover meaningful information for a given class on a samplespecific individual basis. We found ...

Spectral warping is a technique that transforms a digital signal in the time domain by a warping of the frequency axis in its frequency representation. This corresponds to a mapping of the samples in the z-domain such that they are unevenly spaced around the unit circle. Spectral warping can be implemented with a network of linear all-pass filters. The Spectral Warping has a property that a tim...

In this work we extend the test utterance adaptation technique used in vocal tract length normalization to a larger number of speaker characteristic features. We perform partially joint estimation of four features: the VTLN warping factor, the corner position of the piece-wise linear warping function, spectral tilt in voiced segments, and model variance scaling. In experiments on the Swedish PF...