Related papers: Language and Noise Transfer in Speech Enhancement …
Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…
Adversarial training is a promising strategy for enhancing model robustness against adversarial attacks. However, its impact on generalization under substantial data distribution shifts in audio classification remains largely unexplored. To…
Nowadays vast amounts of speech data are recorded from low-quality recorder devices such as smartphones, tablets, laptops, and medium-quality microphones. The objective of this research was to study the automatic generation of high-quality…
With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality…
The human brain contextually exploits heterogeneous sensory information to efficiently perform cognitive tasks including vision and hearing. For example, during the cocktail party situation, the human auditory cortex contextually integrates…
Despite the remarkable progress recently made in distant speech recognition, state-of-the-art technology still suffers from a lack of robustness, especially when adverse acoustic conditions characterized by non-stationary noises and…
Speech enhancement models should meet very low latency requirements typically smaller than 5 ms for hearing assistive devices. While various low-latency techniques have been proposed, comparing these methods in a controlled setup using DNNs…
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of…
We propose a new framework to improve automatic speech recognition (ASR) systems in resource-scarce environments using a generative adversarial network (GAN) operating on acoustic input features. The GAN is used to enhance the features of…
In the realm of automatic speech recognition (ASR), robustness in noisy environments remains a significant challenge. Recent ASR models, such as Whisper, have shown promise, but their efficacy in noisy conditions can be further enhanced.…
Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However, their performance in very low signal-to-noise ratio (SNR)…
The classification of acoustic environments allows for machines to better understand the auditory world around them. The use of deep learning in order to teach machines to discriminate between different rooms is a new area of research.…
In this paper we consider the problem of speech enhancement in real-world like conditions where multiple noises can simultaneously corrupt speech. Most of the current literature on speech enhancement focus primarily on presence of single…
Speech to text models tend to be trained and evaluated against a single target accent. This is especially true for English for which native speakers from the United States became the main benchmark. In this work, we are going to show how…
We present two categories of model-agnostic adversarial strategies that reveal the weaknesses of several generative, task-oriented dialogue models: Should-Not-Change strategies that evaluate over-sensitivity to small and…
In recent years, Generative Adversarial Networks (GANs) have produced significantly improved results in speech enhancement (SE) tasks. They are difficult to train, however. In this work, we introduce several improvements to the GAN training…
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a…
Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource…
State of the art speech enhancement (SE) models achieve strong performance on neurotypical speech, but their effectiveness is substantially reduced for pathological speech. In this paper, we investigate strategies to address this gap for…
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…