相关论文: Adversarial Audio Synthesis with Complex-valued Po…

It has been demonstrated that deep neural networks are prone to noisy examples particular adversarial samples during inference process. The gap between robust deep learning systems in real world applications and vulnerable neural networks…

The complex physics involved in atmospheric turbulence makes it very difficult for ground-based astronomy to build accurate scintillation models and develop efficient methodologies to remove this highly structured noise from valuable…

Polyp detection is crucial for colorectal cancer screening, yet existing models are limited by the scale and diversity of available data. While generative models show promise for data augmentation, current methods mainly focus on enhancing…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing (NLP) and multimodal learning, with successful applications in text generation and speech synthesis, enabling a deeper understanding and…

Compared to traditional electrodynamic loudspeakers, the parametric array loudspeaker (PAL) offers exceptional directivity for audio applications but suffers from significant nonlinear distortions due to its inherent intricate demodulation…

This paper tackles two major problem settings for interpretability of audio processing networks, post-hoc and by-design interpretation. For post-hoc interpretation, we aim to interpret decisions of a network in terms of high-level audio…

In this work, we investigate multilingual speech Pre-Trained models (PTMs) for Audio deepfake detection (ADD). We hypothesize that multilingual PTMs trained on large-scale diverse multilingual data gain knowledge about diverse pitches,…

Humans can imagine a scene from a sound. We want machines to do so by using conditional generative adversarial networks (GANs). By applying the techniques including spectral norm, projection discriminator and auxiliary classifier, compared…

Additive models can be used for interpretable machine learning for their clarity and simplicity. However, In the classical models for high-order data, the vectorization operation disrupts the data structure, which may lead to degenerated…

In this paper, a new deep learning architecture for stereo disparity estimation is proposed. The proposed atrous multiscale network (AMNet) adopts an efficient feature extractor with depthwise-separable convolutions and an extended cost…

In this paper, we study offline preference-based reinforcement learning (PbRL), where learning is based on pre-collected preference feedback over pairs of trajectories. While offline PbRL has demonstrated remarkable empirical success,…

Large Speech Language Models (LSLMs) typically operate at high token rates (tokens/s) to ensure acoustic fidelity, yet this results in sequence lengths that far exceed the underlying semantic content, incurring prohibitive inference costs.…

Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models…

Voice disorders negatively impact the quality of daily life in various ways. However, accurately recognizing the category of pathological features from raw audio remains a considerable challenge due to the limited dataset. A promising…

Adversarial examples pose a significant challenge to the robustness, reliability and alignment of deep neural networks. We propose a novel, easy-to-use approach to achieving high-quality representations that lead to adversarial robustness…

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…

Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise. The…

We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models. Our hypothesis is that perturbations produced in the wavelet space disrupt early…

One of the most challenging goals in designing intelligent systems is empowering them with the ability to synthesize programs from data. Namely, given specific requirements in the form of input/output pairs, the goal is to train a machine…

In this paper, we propose hybrid real- and complex-valued neural networks for speech enhancement. Real- or complex-valued models are either inefficient or present high complexity. We devise a straightforward design method for extending a…