Related papers: Adversarial Privacy Protection on Speech Enhanceme…

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this robustness does not carry over to adversarial noise. We show…

In recent years, deep learning has shown itself to be an incredibly valuable tool in cybersecurity as it helps network intrusion detection systems to classify attacks and detect new ones. Adversarial learning is the process of utilizing…

Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the…

Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. In this paper we…

Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…

A wireless communications system usually consists of a transmitter which transmits the information and a receiver which recovers the original information from the received distorted signal. Deep learning (DL) has been used to improve the…

A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness…

Error correction techniques have been used to refine the output sentences from automatic speech recognition (ASR) models and achieve a lower word error rate (WER). Previous works usually adopt end-to-end models and has strong dependency on…

Recent developments in large speech foundation models like Whisper have led to their widespread use in many automatic speech recognition (ASR) applications. These systems incorporate `special tokens' in their vocabulary, such as…

Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To evaluate their privacy benefits, attacks in the form of automatic speaker verification (ASV) systems…

Speech emotion recognition aims to identify emotional states from speech signals and has been widely applied in human-computer interaction, education, healthcare, and many other fields. However, since speech data contain rich sensitive…

This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR). This problem is especially important in the…

Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they typically require that the ASR model is retrained to cope with…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fooled by artificial…

Deep neural networks have achieved unprecedented success on diverse vision tasks. However, they are vulnerable to adversarial noise that is imperceptible to humans. This phenomenon negatively affects their deployment in real-world…

The current privacy evaluation for speaker anonymization often overestimates privacy when a same-gender target selection algorithm (TSA) is used, although this TSA leaks the speaker's gender and should hence be more vulnerable. We…

Speech model adaptation is crucial to handle the discrepancy between server-side proxy training data and actual data received on local devices of users. With the use of federated learning (FL), we introduce an efficient approach on…

Training models that are robust to data domain shift has gained an increasing interest both in academia and industry. Question-Answering language models, being one of the typical problem in Natural Language Processing (NLP) research, has…