Related papers: A Multiversion Programming Inspired Approach to De…
Pre-trained transformer-based models have significantly advanced automatic speech recognition (ASR), yet they remain sensitive to accent and dialectal variations, resulting in elevated word error rates (WER) in linguistically diverse…
Automatic speech recognition (ASR) models are prevalent, particularly in applications for voice navigation and voice control of domestic appliances. The computational core of ASRs are deep neural networks (DNNs) that have been shown to be…
Under noisy conditions, automatic speech recognition (ASR) can greatly benefit from the addition of visual signals coming from a video of the speaker's face. However, when multiple candidate speakers are visible this traditionally requires…
We investigate the vulnerability of computer-vision-based signal classifiers to adversarial perturbations of their inputs, where the signals and perturbations are subject to physical constraints. We consider a scenario in which a source and…
Today text classification models have been widely used. However, these classifiers are found to be easily fooled by adversarial examples. Fortunately, standard attacking methods generate adversarial texts in a pair-wise way, that is, an…
Adversarial attack approaches to speaker identification either need high computational cost or are not very effective, to our knowledge. To address this issue, in this paper, we propose a novel generation-network-based approach, called…
In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior…
Audio captioning aims at generating natural language descriptions for audio clips automatically. Existing audio captioning models have shown promising improvement in recent years. However, these models are mostly trained via maximum…
Artificial neural networks have been successfully used for many different classification tasks including malware detection and distinguishing between malicious and non-malicious programs. Although artificial neural networks perform very…
Environmental noises and reverberation have a detrimental effect on the performance of automatic speech recognition (ASR) systems. Multi-condition training of neural network-based acoustic models is used to deal with this problem, but it…
Nowadays, research in speech technologies has gotten a lot out thanks to recently created public domain corpora that contain thousands of recording hours. These large amounts of data are very helpful for training the new complex models…
As audio/visual classification models are widely deployed for sensitive tasks like content filtering at scale, it is critical to understand their robustness along with improving the accuracy. This work aims to study several key questions…
For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…
Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…
Deep learning has become a standard approach for the modeling of audio effects, yet strictly black-box modeling remains problematic for time-varying systems. Unlike time-invariant effects, training models on devices with internal modulation…
Generative adversarial networks (GANs) and diffusion models have recently achieved state-of-the-art performance in audio super-resolution (ADSR), producing perceptually convincing wideband audio from narrowband inputs. However, existing…
A critical factor in trustworthy machine learning is to develop robust representations of the training data. Only under this guarantee methods are legitimate to artificially generate data, for example, to counteract imbalanced datasets or…
Modern applications of artificial neural networks have yielded remarkable performance gains in a wide range of tasks. However, recent studies have discovered that such modelling strategy is vulnerable to Adversarial Examples, i.e. examples…
Traditional adversarial examples are typically generated by adding perturbation noise to the input image within a small matrix norm. In practice, un-restricted adversarial attack has raised great concern and presented a new threat to the AI…
Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs), which are maliciously designed to cause dramatic model output errors. In this work, we reveal that normal examples (NEs) are insensitive to the…