Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Jianwei Yu

Jianwei Yu

Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition

Nov 29, 2021
Junhao Xu, Jianwei Yu, Xunying Liu, Helen Meng

Figure 1 for Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition

Figure 2 for Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition

Figure 3 for Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition

Figure 4 for Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition

Access Paper or Ask Questions

Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

Nov 29, 2021
Junhao Xu, Shoukang Hu, Jianwei Yu, Xunying Liu, Helen Meng

Figure 1 for Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

Figure 2 for Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

Figure 3 for Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

Figure 4 for Mixed Precision of Quantization of Transformer Language Models for Speech Recognition

* arXiv admin note: substantial text overlap with arXiv:2112.11438, arXiv:2111.14479

Access Paper or Ask Questions

Deconvolutional Networks on Graph Data

Oct 29, 2021
Jia Li, Jiajin Li, Yang Liu, Jianwei Yu, Yueting Li, Hong Cheng

Figure 1 for Deconvolutional Networks on Graph Data

Figure 2 for Deconvolutional Networks on Graph Data

Figure 3 for Deconvolutional Networks on Graph Data

Figure 4 for Deconvolutional Networks on Graph Data

* arXiv admin note: text overlap with arXiv:2012.11898

Access Paper or Ask Questions

Adversarial Data Augmentation for Disordered Speech Recognition

Aug 02, 2021
Zengrui Jin, Mengzhe Geng, Xurong Xie, Jianwei Yu, Shansong Liu, Xunying Liu, Helen Meng

Figure 1 for Adversarial Data Augmentation for Disordered Speech Recognition

Figure 2 for Adversarial Data Augmentation for Disordered Speech Recognition

Figure 3 for Adversarial Data Augmentation for Disordered Speech Recognition

Figure 4 for Adversarial Data Augmentation for Disordered Speech Recognition

* 5 pages, 3 figures, INTERSPEECH 2021

Access Paper or Ask Questions

TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

Mar 31, 2021
Helin Wang, Bo Wu, Lianwu Chen, Meng Yu, Jianwei Yu, Yong Xu, Shi-Xiong Zhang, Chao Weng, Dan Su, Dong Yu

Figure 1 for TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

Figure 2 for TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

Figure 3 for TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

Figure 4 for TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

* Submitted to Interspeech 2021

Access Paper or Ask Questions

Audio-visual Multi-channel Recognition of Overlapped Speech

May 18, 2020
Jianwei Yu, Bo Wu, Rongzhi Gu Shi-Xiong Zhang Lianwu Chen Yong Xu Meng Yu, Dan Su, Dong Yu, Xunying Liu, Helen Meng

Figure 1 for Audio-visual Multi-channel Recognition of Overlapped Speech

Figure 2 for Audio-visual Multi-channel Recognition of Overlapped Speech

Figure 3 for Audio-visual Multi-channel Recognition of Overlapped Speech

Figure 4 for Audio-visual Multi-channel Recognition of Overlapped Speech

* submitted to Interspeech 2020

Access Paper or Ask Questions

Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification

Apr 08, 2020
Xu Li, Jinghua Zhong, Jianwei Yu, Shoukang Hu, Xixin Wu, Xunying Liu, Helen Meng

Figure 1 for Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification

Figure 2 for Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification

Figure 3 for Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification

Figure 4 for Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification

* Accepted by Speaker Odyssey 2020

Access Paper or Ask Questions