Picture for Hung-Shin Lee

Hung-Shin Lee

Enhancing Low-Resource Minority Language Translation with LLMs and Retrieval-Augmented Generation for Cultural Nuances

Add code
May 16, 2025
Viaarxiv icon

Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions

Add code
Oct 21, 2024
Figure 1 for Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions
Figure 2 for Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions
Viaarxiv icon

Exploring the Impact of Data Quantity on ASR in Extremely Low-resource Languages

Add code
Sep 13, 2024
Viaarxiv icon

Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation

Add code
Sep 03, 2024
Viaarxiv icon

VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka

Add code
Sep 03, 2024
Figure 1 for VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka
Figure 2 for VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka
Figure 3 for VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka
Figure 4 for VoxHakka: A Dialectally Diverse Multi-speaker Text-to-Speech System for Taiwanese Hakka
Viaarxiv icon

Benchmarking Cognitive Domains for LLMs: Insights from Taiwanese Hakka Culture

Add code
Sep 03, 2024
Viaarxiv icon

The North System for Formosa Speech Recognition Challenge 2023

Add code
Oct 06, 2023
Viaarxiv icon

CasNet: Investigating Channel Robustness for Speech Separation

Add code
Oct 27, 2022
Viaarxiv icon

A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference

Add code
Oct 27, 2022
Figure 1 for A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference
Figure 2 for A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference
Figure 3 for A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference
Figure 4 for A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference
Viaarxiv icon

Filter-based Discriminative Autoencoders for Children Speech Recognition

Add code
Apr 01, 2022
Figure 1 for Filter-based Discriminative Autoencoders for Children Speech Recognition
Figure 2 for Filter-based Discriminative Autoencoders for Children Speech Recognition
Figure 3 for Filter-based Discriminative Autoencoders for Children Speech Recognition
Figure 4 for Filter-based Discriminative Autoencoders for Children Speech Recognition
Viaarxiv icon