Picture for Jui-Yang Hsu

Jui-Yang Hsu

Omnizart: A General Toolbox for Automatic Music Transcription

Add code
Jun 01, 2021
Viaarxiv icon

DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation

Add code
May 13, 2020
Figure 1 for DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Figure 2 for DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Figure 3 for DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Figure 4 for DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
Viaarxiv icon

Meta Learning for End-to-End Low-Resource Speech Recognition

Add code
Oct 26, 2019
Figure 1 for Meta Learning for End-to-End Low-Resource Speech Recognition
Figure 2 for Meta Learning for End-to-End Low-Resource Speech Recognition
Figure 3 for Meta Learning for End-to-End Low-Resource Speech Recognition
Figure 4 for Meta Learning for End-to-End Low-Resource Speech Recognition
Viaarxiv icon

Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content

Add code
Jan 01, 2017
Figure 1 for Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
Figure 2 for Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
Figure 3 for Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
Figure 4 for Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content
Viaarxiv icon