33 citations · 212 across the 23 of their papers we have counts for
23 papers
ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs
Xingchen Song, Di Wu, Binbin Zhang +4
In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective \textbf{training-free} methods to decrease…
Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention Frames
Chengdong Liang, Xiao-Lei Zhang, BinBin Zhang +5
Recently, the unified streaming and non-streaming two-pass (U2/U2++) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy…
TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty
Xingchen Song, Di Wu, Zhiyong Wu +6
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 leng…
FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
Xingchen Song, Di Wu, Binbin Zhang +8
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…
OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Siyuan Li, Zedong Wang, Zicheng Liu +5
Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations…
DLME: Deep Local-flatness Manifold Embedding
Zelin Zang, Siyuan Li, Di Wu +5
Manifold learning (ML) aims to seek low-dimensional embedding from high-dimensional data. The problem is challenging on real-world datasets, especially with under-sampling data, an…
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
Siyuan Li, Di Wu, Fang Wu +2
Masked image modeling, an emerging self-supervised pre-training method, has shown impressive success across numerous downstream vision tasks with Vision transformers. Its underlyin…
Neuro-BERT: Rethinking Masked Autoencoding for Self-supervised Neurological Pretraining
Di Wu, Siyuan Li, Jie Yang +1
Deep learning associated with neurological signals is poised to drive major advancements in diverse fields such as medical diagnostics, neurorehabilitation, and brain-computer inte…
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
Binbin Zhang, Di Wu, Zhendong Peng +7
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address…
Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation
Di Wu, Jie Yang, Mohamad Sawan
Objective. Deep neural networks (DNNs) have shown unprecedented success in various brain-machine interface applications such as epileptic seizure prediction. However, existing appr…
Learning to Simulate Unseen Physical Systems with Graph Neural Networks
Ce Yang, Weihao Gao, Di Wu +1
Simulation of the dynamics of physical systems is essential to the development of both science and engineering. Recently there is an increasing interest in learning to simulate the…
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Siyuan Li, Zicheng Liu, Zedong Wang +3
Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training…
GenURL: A General Framework for Unsupervised Representation Learning
Siyuan Li, Zicheng Liu, Zelin Zang +3
Unsupervised representation learning (URL), which learns compact embeddings of high-dimensional data without supervision, has made remarkable progress recently. However, the develo…
CSP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Di Wu, Yi Shi, Ziyu Wang +2
Recent development in brain-machine interface technology has made seizure prediction possible. However, the communication of large volume of electrophysiological signals between se…
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
Binbin Zhang, Hang Lv, Pengcheng Guo +9
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hou…
Exploring Localization for Self-supervised Fine-grained Contrastive Learning
Di Wu, Siyuan Li, Zelin Zang +1
Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classifica…
U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
Di Wu, Binbin Zhang, Chao Yang +4
The unified streaming and non-streaming two-pass (U2) end-to-end model for speech recognition has shown great performance in terms of streaming capability, accuracy, real-time fact…
Unsupervised Deep Manifold Attributed Graph Embedding
Zelin Zang, Siyuan Li, Di Wu +3
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space. Existing meth…
Representation range needs for 16-bit neural network training
Valentina Popescu, Abhinav Venigalla, Di Wu +1
Deep learning has grown rapidly thanks to its state-of-the-art performance across a wide range of real-world applications. While neural networks have been trained using IEEE-754 bi…
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
Zicheng Liu, Siyuan Li, Di Wu +4
Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g.…
WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
Zhuoyuan Yao, Di Wu, Xiong Wang +7
In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify st…
DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning
Di Wu, Huayan Wan, Siping Liu +3
The "mind-controlling" capability has always been in mankind's fantasy. With the recent advancements of electroencephalograph (EEG) techniques, brain-computer interface (BCI) resea…
IoT Data Analytics Using Deep Learning
Xiaofeng Xie, Di Wu, Siping Liu +1
Deep learning is a popular machine learning approach which has achieved a lot of progress in all traditional machine learning areas. Internet of thing (IoT) and Smart City deployme…