26 accepted papers
Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments in video and audio, offering strong interpretability for security and forensics. While recent State Space Models (SSMs) show promise in precise temporal reasoning, their use in TFL is hindered by ambiguous boundaries
Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments within videos or audio streams, providing interpretable evidence for multimedia forensics and security. While most existing TFL methods rely on dense frame-level labels in a fully supervised manner, Weakly Supervised
Low-frame-rate (LFR) Multi-Object Tracking (MOT) is crucial for efficient tracking on edge devices, as it significantly reduces computational and storage demands. However, existing trackers struggle in LFR settings due to large temporal gaps, extreme appearance changes, and motion non-linearity. Whi
Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curricul
Existing end-to-end neural codecs have made great progress in preserving audio quality. Despite their success, they still face challenges in achieving accurate and efficient quantization. Specifically, these codecs often overlook which features have a greater impact on perceptual audio quality durin…
Current deep neural networks for speech enhancement (SE) aim to minimize the distance between the output signal and the clean target by filtering out noise features from input features. However, when noise and speech components are highly similar, SE models struggle to learn effective discrimination…
Speaker recognition (SR) systems are particularly vulnerable to adversarial example (AE) attacks. To mitigate these attacks, AE detection systems are typically integrated into SR systems. To overcome the limitations of low detection accuracy, poor generalization, and high latency in existing schemes…
Spatial audio quality evaluation is essential for applications like virtual and augmented reality, where accurate sound reproduction enhances user immersion. While subjective listening tests are the gold standard, they are costly and time-consuming. To address this, we propose HAPG-SAQAM, an objecti…
Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same SSM to all sub-bands limits its inference capability. Additi…
Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality, controllability, or introduce training complexities. Therefore, w…
Speech enhancement is a vital and highly ill-posed problem for many speech downstream tasks. While currently existing deep learning based speech enhancement methods have held state-of-the-art results, they still possess apparent shortcomings in that most of the deep learning based models lack interp…
Existing deep learning-based speech enhancement methods only adopt clean speech as positive samples to guide the training of speech enhancement networks while negative samples, i.e., noisy speech, are unexploited. In this paper, we adopt contrastive regularization (CR) built upon contrastive learnin…
In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often id…
This study investigates the Lombard effect, where individuals adapt their speech in noisy environments. We introduce an enhanced Mandarin Lombard grid (EMALG) corpus with meaningful sentences, enhancing the Mandarin Lombard grid (MALG) corpus. EMALG features 34 speakers and improves recording setups…
The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or specification-based fine-tuning from which we observe the follow…
"In the past few years, large-scale pre-trained vision-language models like CLIP have achieved tremendous success in various fields. Naturally, how to transfer the rich knowledge in such huge pre-trained models to downstream tasks and datasets becomes a hot topic. During downstream adaptation, the m…
We propose MiT-Net, a novel mix-transformer neural network with a pyramid encoder operating in the time domain, for the task of acoustic echo cancellation. The MiT-Net formulates acoustic echo cancellation as a supervised speech separation problem, in which near-end speech is separated from a single…
Existing automatic sleep staging algorithms rely on accurately labeled data. However, due to the subjectivity of sleep experts, accurate labels must be obtained through joint labeling by multiple experts, which results in high time and labor costs. In this work, we treat labels mislabeled by a singl…
This paper presents a Paired Mandarin Matrix Sentence Dataset (PMMSD), which will be available after publication. PMMSD is the first Mandarin matrix sentence intelligibility dataset containing both plain and Lombard speech for scientific research. The results verify that different Lombard styles wou…
In recent years, deep network pruning has attracted significant attention in order to enable the rapid deployment of AI into small devices with computation and memory constraints. Pruning is often achieved by dropping redundant weights, neurons, or layers of a deep network while attempting to retain…
Attention mechanisms, such as local and non-local attention, play a fundamental role in recent deep learning based speech enhancement (SE) systems. However, a natural speech contains many fast-changing and relatively briefly acoustic events, therefore, capturing the most informative speech features…
The existing face recognition datasets usually lack occlusion samples, which hinders the development of face recognition. Especially during the COVID-19 coronavirus epidemic, wearing a mask has become an effective means of preventing the virus spread. Traditional CNN-based face recognition models tr…
Due to diverse rain shapes, directions, densities as well as different distances to cameras, rain streaks in the air are interweaved and overlapped. However, most existing deraining methods are inherently oblivious this phenomenon and tend to learn a single rain streak layer to simulate this complex…
Most of current best performing Acoustic Scene Classification (ASC) systems utilize Mel scale spectrograms with Convolutional Neural Networks (CNNs). Mel scale is a common way to suit frequency warping of human ears, with strict decreasing frequency resolution on low to high frequency range. However…
NHK has proposed a famous 3D audio system: 22.2 multi-channel system, but its loudspeakers are too many and are troublesome to put in home. Ando and Wang has proposed two simplification methods to reduce its channel number, but only 3D sound field at the central listening point can be recovered well…
This paper proposes a general multichannel system reproduction method. Firstly, relative to original multichannel system, a general global model is build up by guaranteeing sound pressure and the direction of particle velocity at the receiving point constant, and making the square error of particle…