Related papers: Robust Speech Recognition Using Generative Adversa…

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We…

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…

In traditional generative modeling, good data representation is very often a base for a good machine learning model. It can be linked to good representations encoding more explanatory factors that are hidden in the original data. With the…

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize…

Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel…

Despite the recency of their conception, Generative Adversarial Networks (GANs) constitute an extensively researched machine learning sub-field for the creation of synthetic data through deep generative modeling. GANs have consequently been…

Current Generative Adversarial Network (GAN)-based approaches for time series generation face challenges such as suboptimal convergence, information loss in embedding spaces, and instability. To overcome these challenges, we introduce an…

Generative Adversarial Networks (GANs) have experienced a recent surge in popularity, performing competitively in a variety of tasks, especially in computer vision. However, GAN training has shown limited success in natural language…

We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse…

Speech bandwidth expansion is crucial for expanding the frequency range of low-bandwidth speech signals, thereby improving audio quality, clarity and perceptibility in digital applications. Its applications span telephony, compression,…

Generative Adversarial Networks (GANs) is a novel class of deep generative models which has recently gained significant attention. GANs learns complex and high-dimensional distributions implicitly over images, audio, and data. However,…

Lately, the self-attention mechanism has marked a new milestone in the field of automatic speech recognition (ASR). Nevertheless, its performance is susceptible to environmental intrusions as the system predicts the next output symbol…

Due to the development of machine learning and speech processing, speech emotion recognition has been a popular research topic in recent years. However, the speech data cannot be protected when it is uploaded and processed on servers in the…

Robust scatter estimation is a fundamental task in statistics. The recent discovery on the connection between robust estimation and generative adversarial nets (GANs) by Gao et al. (2018) suggests that it is possible to compute depth-like…

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such…

In recent years, Generative Adversarial Networks (GANs) have become a hot topic among researchers and engineers that work with deep learning. It has been a ground-breaking technique which can generate new pieces of content of data in a…

Generative adversarial networks (GANs) have shown potential in learning emotional attributes and generating new data samples. However, their performance is usually hindered by the unavailability of larger speech emotion recognition (SER)…

Training deep neural networks on well-understood dependencies in speech data can provide new insights into how they learn internal representations. This paper argues that acquisition of speech can be modeled as a dependency between random…

In this paper we propose a novel defense approach against end-to-end adversarial attacks developed to fool advanced speech-to-text systems such as DeepSpeech and Lingvo. Unlike conventional defense approaches, the proposed approach does not…

Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause misclassification by…