Výsledky vyhledávání

Report

Federated Learning via Variational Bayesian Inference: Personalization, Sparsity and Clustering

Autor: Zhang, Xu, Li, Wenpeng, Shao, Yunfeng, Li, Yinchuan

Federated learning (FL) is a promising framework that models distributed machine learning while protecting the privacy of clients. However, FL suffers performance degradation from heterogeneous and limited data. To alleviate the degradation, we prese

Externí odkaz: http://arxiv.org/abs/2303.04345

Zobrazit plný text záznamu

Report

TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty

Autor: Song, Xingchen, Wu, Di, Wu, Zhiyong, Zhang, Binbin, Zhang, Yuekai, Peng, Zhendong, Li, Wenpeng, Pan, Fuping, Zhu, Changbao

In this paper, we present TrimTail, a simple but effective emission regularization method to improve the latency of streaming ASR models. The core idea of TrimTail is to apply length penalty (i.e., by trimming trailing frames, see Fig. 1-(b)) directl

Externí odkaz: http://arxiv.org/abs/2211.00522

Zobrazit plný text záznamu

Report

FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition

Autor: Song, Xingchen, Wu, Di, Zhang, Binbin, Wu, Zhiyong, Li, Wenpeng, Li, Dongfang, Zhang, Pengshen, Peng, Zhendong, Pan, Fuping, Zhu, Changbao, Wu, Zhongqin

The recently proposed Conformer architecture which combines convolution with attention to capture both local and global dependencies has become the \textit{de facto} backbone model for Automatic Speech Recognition~(ASR). Inherited from the Natural La

Externí odkaz: http://arxiv.org/abs/2210.17079

Zobrazit plný text záznamu

Report

Personalized Federated Learning via Variational Bayesian Inference

Autor: Zhang, Xu, Li, Yinchuan, Li, Wenpeng, Guo, Kaiyang, Shao, Yunfeng

Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel personalized federated learning method via Bayesian variational

Externí odkaz: http://arxiv.org/abs/2206.07977

Zobrazit plný text záznamu

Report

Machine-learned control-oriented flow estimation for multiactuator multi-sensor systems exemplified for the fluidic pinball

Autor: Li, Songqi, Li, Wenpeng, Noack, Bernd R.

We propose the first machine-learned control-oriented flow estimation for multiple-input multiple-output plants. Starting point is constant actuation with open-loop actuation commands leading to a database with simultaneously recorded actuation comma

Externí odkaz: http://arxiv.org/abs/2205.08334

Zobrazit plný text záznamu