Tao Wei

According to our database, Tao Wei authored at least 13 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation.

Yong Zhang, Bingyuan Zhang, Zhitao Li, Ming Li, Ning Cheng, Minchuan Chen, Tao Wei, Jun Ma, Shaojun Wang, Jing Xiao

CoRR, February, 2025

EffectiveASR: A Single-Step Non-Autoregressive Mandarin Speech Recognition Architecture with High Accuracy and Inference Speed.

Ziyang Zhuang, Chenfeng Miao, Kun Zou, Ming Fang, Tao Wei, Zijian Li, Ning Cheng, Wei Hu, Shaojun Wang, Jing Xiao

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation.

Yong Zhang, Bingyuan Zhang, Zhitao Li, Ming Li, Ning Cheng, Minchuan Chen, Tao Wei, Jun Ma, Shaojun Wang, Jing Xiao

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Token-Level Contextual Network with Ladder-Shaped Attention for End-to-End ASR.

Ming Fang, Kai Guo, Tao Wei, Ziyang Zhuang, Yan Shi, Ning Cheng, Shaojun Wang, Jing Xiao

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

Improving Contextual ASR with Enhanced Phrase-Level Representation Based on MCTC Loss.

Ming Fang, Tao Wei, Kai Guo, Ziyang Zhuang, Yan Shi, Ning Cheng, Shaojun Wang, Jing Xiao

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

A Single-Step Non-Autoregressive Automatic Speech Recognition Architecture with High Accuracy and Inference Speed.

Ziyang Zhuang, Chenfeng Miao, Kun Zou, Shuai Gong, Ming Fang, Tao Wei, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao

CoRR, 2024

E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition.

Kun Zou, Fengyun Tan, Ziyang Zhuang, Chenfeng Miao, Tao Wei, Shaodan Zhai, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao

Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Improving Attention-Based End-to-End Speech Recognition by Monotonic Alignment Attention Matrix Reconstruction.

Ziyang Zhuang, Kun Zou, Chenfeng Miao, Ming Fang, Tao Wei, Zijian Li, Wei Hu, Shaojun Wang, Jing Xiao

Proceedings of the IEEE International Conference on Acoustics, 2024

2023

Improving End-to-End Modeling For Mandarin-English Code-Switching Using Lightweight Switch-Routing Mixture-of-Experts.

Fengyun Tan, Chaofeng Feng, Tao Wei, Shuai Gong, Jinqiang Leng, Wei Chu, Jun Ma, Shaojun Wang, Jing Xiao

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification.

Yuanyuan Wang, Yang Zhang, Zhiyong Wu, Zhihan Yang, Tao Wei, Kun Zou, Helen Meng

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

FFM: A Frame Filtering Mechanism To Accelerate Inference Speed For Conformer In Speech Recognition.

Zongfeng Quan, Nick J. C. Wang, Wei Chu, Tao Wei, Shaojun Wang, Jing Xiao

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

Towards Efficiently Learning Monotonic Alignments for Attention-based End-to-End Speech Recognition.

Chenfeng Miao, Kun Zou, Ziyang Zhuang, Tao Wei, Jun Ma, Shaojun Wang, Jing Xiao

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

SEQ-CPC : Sequential Contrastive Predictive Coding for Automatic Speech Recognition.

Yulong Chen, Jianping Zhao, Weiqi Wang, Ming Fang, Haimei Kang, Lu Wang, Tao Wei, Jun Ma, Shaojun Wang, Jing Xiao

Proceedings of the IEEE International Conference on Acoustics, 2021