Related papers: Self Voice Conversion as an Attack against Neural …

Digital watermarking is a technique of information adding or information hiding in order to identify the owner of the data in multimedia content. It seems that a signal or digital image can permanently embed over another digital data…

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…

Voice conversion has made great progress in the past few years under the studio-quality test scenario in terms of speech quality and speaker similarity. However, in real applications, test speech from source speaker or target speaker can be…

Existing audio watermarking methods usually treat the host audio signals of a function of time or frequency individually, while considering them in the joint time-frequency (TF) domain has received less attention. This paper proposes an…

Now-a-days, speech-based biometric systems such as automatic speaker verification (ASV) are highly prone to spoofing attacks by an imposture. With recent development in various voice conversion (VC) and speech synthesis (SS) algorithms,…

Deep speech classification tasks, mainly including keyword spotting and speaker verification, play a crucial role in speech-based human-computer interaction. Recently, the security of these technologies has been demonstrated to be…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform. The development of high-performing neural network sound recognition systems has raised the possibility of…

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these…

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…

In recent times, communication through the internet has tremendously facilitated the distribution of multimedia data. Although this is indubitably a boon, one of its repercussions is that it has also given impetus to the notorious issue of…

As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores…

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement…

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these…

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

The expansion of the open source community and the rise of large language models have raised ethical and security concerns on the distribution of source code, such as misconduct on copyrighted code, distributions without proper licenses, or…