Related papers: A Joint Noise Disentanglement and Adversarial Trai…

Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data. Performing data augmentation on raw waveforms, such as adding noise or…

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive…

Recently, cycle-consistent adversarial network (Cycle-GAN) has been successfully applied to voice conversion to a different speaker without parallel data, although in those approaches an individual model is needed for each target speaker.…

Spoofing-robust speaker verification (SASV) combines the tasks of speaker and spoof detection to authenticate speakers under adversarial settings. Many SASV systems rely on fusion of speaker and spoof cues at embedding, score or decision…

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the…

Speech 'in-the-wild' is a handicap for speaker recognition systems due to the variability induced by real-life conditions, such as environmental noise and the emotional state of the speaker. Taking advantage of the principles of…

Neural network-based speaker recognition has achieved significant improvement in recent years. A robust speaker representation learns meaningful knowledge from both hard and easy samples in the training set to achieve good performance.…

In this paper, we propose a noise robust bottleneck feature representation which is generated by an adversarial network (AN). The AN includes two cascade connected networks, an encoding network (EN) and a discriminative network (DN).…

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…

When a speaker verification (SV) system operates far from the sound sourced, significant challenges arise due to the interference of noise and reverberation. Studies have shown that incorporating phonetic information into speaker embedding…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

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…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

Deep neural networks (DNNs) are vulnerable to adversarial noise. Their adversarial robustness can be improved by exploiting adversarial examples. However, given the continuously evolving attacks, models trained on seen types of adversarial…

The goal of this paper is to learn robust speaker representation for bilingual speaking scenario. The majority of the world's population speak at least two languages; however, most speaker recognition systems fail to recognise the same…

Noise-robust speaker verification leverages joint learning of speech enhancement (SE) and speaker verification (SV) to improve robustness. However, prevailing approaches rely on implicit noise suppression, which struggles to separate noise…

Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and…

We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate…

This paper introduces a novel deep learning framework for robust image zero-watermarking based on distortion-invariant feature learning. As a zero-watermarking scheme, our method leaves the original image unaltered and learns a reference…

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…