We present a new method for unsupervised, fast speaker adaptation that combines the Eigen-MLLR transform approach with discriminative MLLR. We thereby aim to profit both from the performance improvements that are generally provided by a discriminative approach, and from the reliability that Eigen-MLLR has demonstrated in fast adaptation scenarios. We present first evaluation results on the Spok...

This paper describes a method of fingerprint classification using Eigen Block Directional Fingerprints. The method we propose dispenses off with the preprocessing stages such as segmentation, binarisation, thinning etc. We determine the block directional representation of a fingerprint and the location of the core points in a set of template fingerprints which belong to the same class. In the n...

In [1] a method of decomposing a 3D wave field into spherical harmonics (’eigen-beams’) by using spherical microphone arrays was introduced. It was further shown how the eigen-beams can be used for beamforming applications by means of a modal beamformer structure. This paper introduces a method for the unambiguous localization of multiple wideband acoustic sources in 3D space using the eigen-be...

A phase-sensitive setup for near-field acoustic holography was established in order to determine the characteristic resonance modes of a vibrating membrane. The experiment was carried out using a frame drum as the vibrating system of interest. By exciting the membrane at certain fundamental frequencies and recording the complex signals from the pressure and particle velocity fields across the d...

The gravity field and derivatives generated with the high resolution EIGEN-6C2 gravity model which includes satellite gravity data of GOCE (Gravity field and steady-state Ocean Circulation Explorer) has been utilized for geological appraisal of the Singhbhum-Orissa Craton, India. The GOCE only field gravity data and in situ gravity data of the same area have been utilized for comparative assess...

The purpose of this feasibility research was to study a novel sensor based separation method for recycling of plastic materials from end-of-life vehicles (ELVs) by using eigen-frequency response of impact acoustic emission. In this research three kinds of commonly used plastics, polypropylene (PP), acrylonitrile-butadiene-styrene (ABS), and styrene-maleic-anhydride (SMA) sampled from end-of-lif...