The aim of this paper is to give an overview of domain adaptation and transfer learning with
a specific view on visual applications. After a general motivation, we first position domain …

Eliminating the negative effect of non-stationary environmental noise is a long-standing
research topic for automatic speech recognition but still remains an important challenge …

A key learning scenario in large-scale applications is that of federated learning, where a
centralized model is trained based on data originating from a large number of clients. We …

In machine learning, if the training data is an unbiased sample of an underlying distribution,
then the learned classification function will make accurate predictions for new samples …

Inspired by recent successes of deep learning in computer vision and speech recognition,
we propose a novel framework to encode time series data as different types of images …

While biometric authentication has advanced significantly in recent years, evidence shows
the technology can be susceptible to malicious spoofing attacks. The research community …

Successful speech perception requires that listeners map the acoustic signal to linguistic
categories. These mappings are not only probabilistic, but change depending on the …

In real-world applications of visual recognition, many factors-such as pose, illumination, or
image quality-can cause a significant mismatch between the source domain on which …

We describe the design of Kaldi, a free, open-source toolkit for speech recognition research.
Kaldi provides a speech recognition system based on finite-state transducers (using the …

This paper investigates data augmentation for deep neural network acoustic modeling
based on label-preserving transformations to deal with data sparsity. Two data …