Picture for Haoneng Luo

Haoneng Luo

Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System

Add code
May 25, 2023
Figure 1 for Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System
Figure 2 for Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System
Figure 3 for Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System
Figure 4 for Accurate and Reliable Confidence Estimation Based on Non-Autoregressive End-to-End Speech Recognition System
Viaarxiv icon

FunASR: A Fundamental End-to-End Speech Recognition Toolkit

Add code
May 18, 2023
Viaarxiv icon

Boundary and Context Aware Training for CIF-based Non-Autoregressive End-to-end ASR

Add code
Apr 10, 2021
Viaarxiv icon

Simplified Self-Attention for Transformer-based End-to-End Speech Recognition

Add code
May 21, 2020
Figure 1 for Simplified Self-Attention for Transformer-based End-to-End Speech Recognition
Figure 2 for Simplified Self-Attention for Transformer-based End-to-End Speech Recognition
Figure 3 for Simplified Self-Attention for Transformer-based End-to-End Speech Recognition
Figure 4 for Simplified Self-Attention for Transformer-based End-to-End Speech Recognition
Viaarxiv icon