Picture for Yi-Chang Chen

Yi-Chang Chen

Let's Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Multi-modal Text Recognition

Add code
May 23, 2024
Viaarxiv icon

Breeze-7B Technical Report

Add code
Mar 05, 2024
Viaarxiv icon

Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite

Add code
Oct 02, 2023
Figure 1 for Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite
Figure 2 for Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite
Figure 3 for Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suite
Viaarxiv icon

Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning

Add code
Jul 18, 2023
Viaarxiv icon

g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin

Add code
Mar 24, 2022
Figure 1 for g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin
Figure 2 for g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin
Figure 3 for g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin
Figure 4 for g2pW: A Conditional Weighted Softmax BERT for Polyphone Disambiguation in Mandarin
Viaarxiv icon

SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition

Add code
Feb 24, 2022
Figure 1 for SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition
Figure 2 for SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition
Figure 3 for SMILE: Sequence-to-Sequence Domain Adaption with Minimizing Latent Entropy for Text Image Recognition
Viaarxiv icon

Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition

Add code
Nov 26, 2021
Figure 1 for Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
Figure 2 for Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
Figure 3 for Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
Figure 4 for Traditional Chinese Synthetic Datasets Verified with Labeled Data for Scene Text Recognition
Viaarxiv icon

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

Add code
Nov 16, 2021
Viaarxiv icon

A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening

Add code
Apr 30, 2020
Figure 1 for A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening
Figure 2 for A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening
Figure 3 for A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening
Figure 4 for A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening
Viaarxiv icon