Picture for Jian Luo

Jian Luo

Accelerating PDE Data Generation via Differential Operator Action in Solution Space

Add code
Feb 04, 2024
Viaarxiv icon

BC4LLM: Trusted Artificial Intelligence When Blockchain Meets Large Language Models

Add code
Oct 10, 2023
Viaarxiv icon

Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy

Add code
Mar 14, 2023
Viaarxiv icon

Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation

Add code
Jun 30, 2022
Figure 1 for Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation
Figure 2 for Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation
Figure 3 for Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation
Figure 4 for Tiny-Sepformer: A Tiny Time-Domain Transformer Network for Speech Separation
Viaarxiv icon

Speech Augmentation Based Unsupervised Learning for Keyword Spotting

Add code
May 28, 2022
Figure 1 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Figure 2 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Figure 3 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Figure 4 for Speech Augmentation Based Unsupervised Learning for Keyword Spotting
Viaarxiv icon

Adaptive Activation Network For Low Resource Multilingual Speech Recognition

Add code
May 28, 2022
Figure 1 for Adaptive Activation Network For Low Resource Multilingual Speech Recognition
Figure 2 for Adaptive Activation Network For Low Resource Multilingual Speech Recognition
Figure 3 for Adaptive Activation Network For Low Resource Multilingual Speech Recognition
Figure 4 for Adaptive Activation Network For Low Resource Multilingual Speech Recognition
Viaarxiv icon

Loss Prediction: End-to-End Active Learning Approach For Speech Recognition

Add code
Jul 09, 2021
Figure 1 for Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
Figure 2 for Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
Figure 3 for Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
Figure 4 for Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
Viaarxiv icon

Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation

Add code
Jul 09, 2021
Figure 1 for Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
Figure 2 for Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
Figure 3 for Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
Figure 4 for Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
Viaarxiv icon

Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition

Add code
Feb 23, 2021
Figure 1 for Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition
Figure 2 for Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition
Figure 3 for Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition
Figure 4 for Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition
Viaarxiv icon

Low Latency Scheduling Algorithms for Full-Duplex V2X Networks

Add code
Jan 13, 2021
Figure 1 for Low Latency Scheduling Algorithms for Full-Duplex V2X Networks
Figure 2 for Low Latency Scheduling Algorithms for Full-Duplex V2X Networks
Figure 3 for Low Latency Scheduling Algorithms for Full-Duplex V2X Networks
Figure 4 for Low Latency Scheduling Algorithms for Full-Duplex V2X Networks
Viaarxiv icon