Picture for Shiyi Han

Shiyi Han

Enhancing CTC-based speech recognition with diverse modeling units

Add code
Jun 05, 2024
Viaarxiv icon

Conformer-Based Speech Recognition On Extreme Edge-Computing Devices

Add code
Dec 16, 2023
Viaarxiv icon

Personalization of CTC-based End-to-End Speech Recognition Using Pronunciation-Driven Subword Tokenization

Add code
Oct 16, 2023
Viaarxiv icon

Acoustic Model Fusion for End-to-end Speech Recognition

Add code
Oct 10, 2023
Viaarxiv icon

Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices

Add code
Jul 18, 2022
Figure 1 for Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Figure 2 for Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Figure 3 for Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Figure 4 for Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices
Viaarxiv icon