Jun Chen

Jun Chen, Zilin Wang, Deyi Tuo et al.

Previously proposed FullSubNet has achieved outstanding performance in Deep Noise Suppression (DNS) Challenge and attracted much attention. However, it still encounters issues such as input-output mismatch and coarse processing for frequency bands. In this paper, we propose an extended single-channel real-time speech enhancement framework called FullSubNet+ with following significant improvements. First, we design a lightweight multi-scale time sensitive channel attention (MulCA) module which adopts multi-scale convolution and channel attention mechanism to help the network focus on more discriminative frequency bands for noise reduction. Then, to make full use of the phase information in noisy speech, our model takes all the magnitude, real and imaginary spectrograms as inputs. Moreover, by replacing the long short-term memory (LSTM) layers in original full-band model with stacked temporal convolutional network (TCN) blocks, we design a more efficient full-band module called full-band extractor. The experimental results in DNS Challenge dataset show the superior performance of our FullSubNet+, which reaches the state-of-the-art (SOTA) performance and outperforms other existing speech enhancement approaches.

Xiaoqian Shen, Yunyang Xiong, Changsheng Zhao et al.

Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM's context size. To address this limitation, we propose LongVU, a spatiotemporal adaptive compression mechanism thats reduces the number of video tokens while preserving visual details of long videos. Our idea is based on leveraging cross-modal query and inter-frame dependencies to adaptively reduce temporal and spatial redundancy in videos. Specifically, we leverage DINOv2 features to remove redundant frames that exhibit high similarity. Then we utilize text-guided cross-modal query for selective frame feature reduction. Further, we perform spatial token reduction across frames based on their temporal dependencies. Our adaptive compression strategy effectively processes a large number of frames with little visual information loss within given context length. Our LongVU consistently surpass existing methods across a variety of video understanding benchmarks, especially on hour-long video understanding tasks such as VideoMME and MLVU. Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance.

Jun Chen, Weng-Keen Wong, Bechir Hamdaoui

Radio Frequency (RF) device fingerprinting has been recognized as a potential technology for enabling automated wireless device identification and classification. However, it faces a key challenge due to the domain shift that could arise from variations in the channel conditions and environmental settings, potentially degrading the accuracy of RF-based device classification when testing and training data is collected in different domains. This paper introduces a novel solution that leverages contrastive learning to mitigate this domain shift problem. Contrastive learning, a state-of-the-art self-supervised learning approach from deep learning, learns a distance metric such that positive pairs are closer (i.e. more similar) in the learned metric space than negative pairs. When applied to RF fingerprinting, our model treats RF signals from the same transmission as positive pairs and those from different transmissions as negative pairs. Through experiments on wireless and wired RF datasets collected over several days, we demonstrate that our contrastive learning approach captures domain-invariant features, diminishing the effects of domain-specific variations. Our results show large and consistent improvements in accuracy (10.8\% to 27.8\%) over baseline models, thus underscoring the effectiveness of contrastive learning in improving device classification under domain shift.

Siqi Li, Jun Chen, Jingyang Xiang et al.

Structured pruning methods are developed to bridge the gap between the massive scale of neural networks and the limited hardware resources. Most current structured pruning methods rely on training datasets to fine-tune the compressed model, resulting in high computational burdens and being inapplicable for scenarios with stringent requirements on privacy and security. As an alternative, some data-free methods have been proposed, however, these methods often require handcraft parameter tuning and can only achieve inflexible reconstruction. In this paper, we propose the Automatic Data-Free Pruning (AutoDFP) method that achieves automatic pruning and reconstruction without fine-tuning. Our approach is based on the assumption that the loss of information can be partially compensated by retaining focused information from similar channels. Specifically, We formulate data-free pruning as an optimization problem, which can be effectively addressed through reinforcement learning. AutoDFP assesses the similarity of channels for each layer and provides this information to the reinforcement learning agent, guiding the pruning and reconstruction process of the network. We evaluate AutoDFP with multiple networks on multiple datasets, achieving impressive compression results. For instance, on the CIFAR-10 dataset, AutoDFP demonstrates a 2.87\% reduction in accuracy loss compared to the recently proposed data-free pruning method DFPC with fewer FLOPs on VGG-16. Furthermore, on the ImageNet dataset, AutoDFP achieves 43.17\% higher accuracy than the SOTA method with the same 80\% preserved ratio on MobileNet-V1.

Zhiwei Lin, Jun Chen, Boshi Tang et al.

Variational Autoencoders (VAEs) constitute a crucial component of neural symbolic music generation, among which some works have yielded outstanding results and attracted considerable attention. Nevertheless, previous VAEs still encounter issues with overly long feature sequences and generated results lack contextual coherence, thus the challenge of modeling long multi-track symbolic music still remains unaddressed. To this end, we propose Multi-view MidiVAE, as one of the pioneers in VAE methods that effectively model and generate long multi-track symbolic music. The Multi-view MidiVAE utilizes the two-dimensional (2-D) representation, OctupleMIDI, to capture relationships among notes while reducing the feature sequences length. Moreover, we focus on instrumental characteristics and harmony as well as global and local information about the musical composition by employing a hybrid variational encoding-decoding strategy to integrate both Track- and Bar-view MidiVAE features. Objective and subjective experimental results on the CocoChorales dataset demonstrate that, compared to the baseline, Multi-view MidiVAE exhibits significant improvements in terms of modeling long multi-track symbolic music.

Jun Chen, Chaokun Wang

To stretch a music piece to a given length is a common demand in people's daily lives, e.g., in audio-video synchronization and animation production. However, it is not always guaranteed that the stretched music piece is acceptable for general audience since music stretching suffers from people's perceptual artefacts. Over-stretching a music piece will make it uncomfortable for human psychoacoustic hearing. The research on music stretching resistance attempts to estimate the maximum stretchability of music pieces to further avoid over-stretch. It has been observed that musical genres can significantly improve the accuracy of automatic estimation of music stretching resistance, but how musical genres are related to music stretching resistance has never been explained or studied in detail in the literature. In this paper, the characteristics of music stretching resistance are compared across different musical genres. It is found that music stretching resistance has strong intra-genre cohesiveness and inter-genre discrepancies in the experiments. Moreover, the ambiguity and the symmetry of music stretching resistance are also observed in the experimental analysis. These findings lead to a new measurement on the similarity between different musical genres based on their music stretching resistance. In addition, the analysis of variance (ANOVA) also supports the findings in this paper by verifying the significance of musical genre in shaping music stretching resistance.