Zobrazeno 1 - 10
of 4 585
pro vyhledávání: '"Kang,Wei"'
The growing privacy concerns in distributed learning have led to the widespread adoption of secure aggregation techniques in distributed machine learning systems, such as federated learning. Motivated by a coded gradient aggregation problem in a user
Externí odkaz:
http://arxiv.org/abs/2412.11496
Autor:
Yang, Yifan, Zhuo, Jianheng, Jin, Zengrui, Ma, Ziyang, Yang, Xiaoyu, Yao, Zengwei, Guo, Liyong, Kang, Wei, Kuang, Fangjun, Lin, Long, Povey, Daniel, Chen, Xie
Self-supervised learning (SSL) has achieved great success in speech-related tasks, driven by advancements in speech encoder architectures and the expansion of datasets. While Transformer and Conformer architectures have dominated SSL backbones, encod
Externí odkaz:
http://arxiv.org/abs/2411.17100
Autor:
Yao, Zengwei, Kang, Wei, Yang, Xiaoyu, Kuang, Fangjun, Guo, Liyong, Zhu, Han, Jin, Zengrui, Li, Zhaoqing, Lin, Long, Povey, Daniel
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency. However, it often falls short in recognition performance. In this work, we propose t
Externí odkaz:
http://arxiv.org/abs/2410.05101
Autor:
Jin, Zengrui, Yang, Yifan, Shi, Mohan, Kang, Wei, Yang, Xiaoyu, Yao, Zengwei, Kuang, Fangjun, Guo, Liyong, Meng, Lingwei, Lin, Long, Xu, Yong, Zhang, Shi-Xiong, Povey, Daniel
The evolving speech processing landscape is increasingly focused on complex scenarios like meetings or cocktail parties with multiple simultaneous speakers and far-field conditions. Existing methodologies for addressing these challenges fall into two
Externí odkaz:
http://arxiv.org/abs/2409.00819
Autor:
Chu, Detian, Bai, Linyuan, Huang, Jianuo, Fang, Zhenlong, Zhang, Peng, Kang, Wei, Lin, Haifeng
With the advancement of autonomous driving, ensuring safety during motion planning and navigation is becoming more and more important. However, most end-to-end planning methods suffer from a lack of safety. This research addresses the safety issue in
Externí odkaz:
http://arxiv.org/abs/2407.06317
We investigate the demand private coded caching problem, which is an $(N,K)$ coded caching problem with $N$ files, $K$ users, each equipped with a cache of size $M$, and an additional privacy constraint on user demands. We first present a new virtual
Externí odkaz:
http://arxiv.org/abs/2404.06884
In order to solve the problem that current convolutional neural networks can not capture the correlation features between the time domain signals of rolling bearings effectively, and the model accuracy is limited by the number and quality of samples,
Externí odkaz:
http://arxiv.org/abs/2403.15483
Autor:
Shen, Jingxiang, Kang, Wei
For the data analysis problem of shock-ramp compression, i.e., ramp compression after a relatively strong initial shock, a characteristics-based method that strictly deals with the initial hydrodynamic shock is described in detail. Validation of this
Externí odkaz:
http://arxiv.org/abs/2403.13380
In this paper, we consider the case that sharing many secrets among a set of participants using the threshold schemes. All secrets are assumed to be statistically independent and the weak secure condition is focused on. Under such circumstances we in
Externí odkaz:
http://arxiv.org/abs/2312.05737
We investigate the multi-access coded caching problem, which involves $N$ files, $K$ users, and $K$ caches in this paper. Each user can access $L$ adjacent caches in a cyclic manner. We present a coded placement scheme for the case of cache $M=\frac{
Externí odkaz:
http://arxiv.org/abs/2312.04922