Picture for Pin-Jui Ku

Pin-Jui Ku

A Bottom-up Framework with Language-universal Speech Attribute Modeling for Syllable-based ASR

Add code
Sep 09, 2025
Viaarxiv icon

An Investigation on Combining Geometry and Consistency Constraints into Phase Estimation for Speech Enhancement

Add code
Jul 02, 2025
Viaarxiv icon

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration

Add code
Sep 25, 2024
Viaarxiv icon

An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement

Add code
Sep 24, 2024
Figure 1 for An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement
Figure 2 for An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement
Figure 3 for An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement
Figure 4 for An Explicit Consistency-Preserving Loss Function for Phase Reconstruction and Speech Enhancement
Viaarxiv icon

Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition

Add code
Jun 04, 2024
Figure 1 for Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
Figure 2 for Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
Figure 3 for Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
Figure 4 for Language-Universal Speech Attributes Modeling for Zero-Shot Multilingual Spoken Keyword Recognition
Viaarxiv icon

A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models

Add code
Jun 01, 2023
Figure 1 for A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models
Figure 2 for A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models
Figure 3 for A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models
Figure 4 for A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models
Viaarxiv icon

A Neural State-Space Model Approach to Efficient Speech Separation

Add code
May 26, 2023
Figure 1 for A Neural State-Space Model Approach to Efficient Speech Separation
Figure 2 for A Neural State-Space Model Approach to Efficient Speech Separation
Figure 3 for A Neural State-Space Model Approach to Efficient Speech Separation
Figure 4 for A Neural State-Space Model Approach to Efficient Speech Separation
Viaarxiv icon

A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming

Add code
Oct 08, 2021
Figure 1 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Figure 2 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Figure 3 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Figure 4 for A Study of Low-Resource Speech Commands Recognition based on Adversarial Reprogramming
Viaarxiv icon

The AS-NU System for the M2VoC Challenge

Add code
Apr 07, 2021
Figure 1 for The AS-NU System for the M2VoC Challenge
Figure 2 for The AS-NU System for the M2VoC Challenge
Figure 3 for The AS-NU System for the M2VoC Challenge
Figure 4 for The AS-NU System for the M2VoC Challenge
Viaarxiv icon