State-of-the-art speech representations provide acceptable recognition results under optimal conditions, though their performance in adverse conditions still needs to be improved. In this direction, many advances involving ...

The determination of quality of the signals obtained by blind source separation is a very important subject fordevelopment and evaluation of such algorithms. When this approach is used as a pre-processing stage for automatic ...

Recent progress in deep learning has revolutionized speech recognition research, with Deep Neural Networks (DNNs) becoming the new state of the art for acoustic modeling. DNNs offer significantly lower speech recognition ...

A novel scheme for disambiguating conflicting classification results in Audio-Visual Speech Recognition (AVSR) applications is proposed in this paper. The classification scheme can be implemented with both generative and ...

This paper proposes a robust front-end for speech classification which can be employed with acoustic, visual or audio–visual information, indistinctly. Wavelet multiresolution analysis is employed to represent temporal ...

Hidden Markov models have been found very useful for a wide range of applications in machine learning and pattern recognition. The wavelet transform has emerged as a new tool for signal and image analysis. Learning models ...

In this work, we propose a novel re-sampling method based on word lattice information and we use prosodic cues with support vector machines for classification. The idea is to consider word recognition as a two-class ...

Evolutionary algorithms provide flexibility and robustness required to find satisfactory solutions in complex search spaces. This is why they are successfully applied for solving real engineering problems. In this work we ...