Adversarial attacks represent a security threat to machine learning base...
This work presents an ensemble system based on various uni-modal and bi-...
In the past few years, it has been shown that deep learning systems are
...
With the growing availability of smart devices and cloud services, perso...
Audio-visual speech recognition (AVSR) can effectively and significantly...
The PAN 2021 authorship verification (AV) challenge is part of a three-y...
We are addressing two fundamental problems in authorship verification (A...
Sound event localization aims at estimating the positions of sound sourc...
End-to-end acoustic speech recognition has quickly gained widespread
pop...
The detection of voiced speech, the estimation of the fundamental freque...
Sound event localization frameworks based on deep neural networks have s...
Estimating the positions of multiple speakers can be helpful for tasks l...
Adversarial examples seem to be inevitable. These specifically crafted i...
In the past few years, we observed a wide adoption of practical systems ...
The PAN 2020 authorship verification (AV) challenge focuses on a
cross-t...
Voice assistants like Amazon's Alexa, Google's Assistant, or Apple's Sir...
For many small- and medium-vocabulary tasks, audio-visual speech recogni...
Traditional computational authorship attribution describes a classificat...
Machine learning systems and also, specifically, automatic speech recogn...
Deep neural networks can generate images that are astonishingly realisti...
The emerging field of neural speech recognition (NSR) using
electrocorti...
Authorship verification is the task of analyzing the linguistic patterns...
Authorship verification tries to answer the question if two documents wi...
Automatic speech recognition (ASR) systems are possible to fool via targ...
Automatic speech recognition (ASR) systems are possible to fool via targ...
Identification and localization of sounds are both integral parts of
com...
Data fusion plays an important role in many technical applications that
...
Voice interfaces are becoming accepted widely as input methods for a div...