Picture for Xingyu Na

Xingyu Na

Focused Discriminative Training For Streaming CTC-Trained Automatic Speech Recognition Models

Add code
Aug 23, 2024
Viaarxiv icon

Enhancing CTC-based speech recognition with diverse modeling units

Add code
Jun 05, 2024
Viaarxiv icon

A Treatise On FST Lattice Based MMI Training

Add code
Oct 17, 2022
Figure 1 for A Treatise On FST Lattice Based MMI Training
Figure 2 for A Treatise On FST Lattice Based MMI Training
Figure 3 for A Treatise On FST Lattice Based MMI Training
Viaarxiv icon

AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale

Add code
Sep 13, 2018
Figure 1 for AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
Figure 2 for AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
Figure 3 for AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale
Viaarxiv icon

AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline

Add code
Sep 16, 2017
Figure 1 for AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
Figure 2 for AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
Figure 3 for AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
Figure 4 for AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline
Viaarxiv icon