Alert button
Picture for Hsin-Min Wang

Hsin-Min Wang

Alert button

Partially Fake Audio Detection by Self-attention-based Fake Span Discovery

Feb 15, 2022
Haibin Wu, Heng-Cheng Kuo, Naijun Zheng, Kuo-Hsuan Hung, Hung-Yi Lee, Yu Tsao, Hsin-Min Wang, Helen Meng

Figure 1 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Figure 2 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Figure 3 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Figure 4 for Partially Fake Audio Detection by Self-attention-based Fake Span Discovery
Viaarxiv icon

EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement

Feb 14, 2022
Kuan-Chen Wang, Kai-Chun Liu, Hsin-Min Wang, Yu Tsao

Figure 1 for EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement
Figure 2 for EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement
Figure 3 for EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement
Figure 4 for EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement
Viaarxiv icon

Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features

Dec 01, 2021
Ryandhimas E. Zezario, Szu-Wei Fu, Fei Chen, Chiou-Shann Fuh, Hsin-Min Wang, Yu Tsao

Figure 1 for Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features
Figure 2 for Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features
Figure 3 for Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features
Figure 4 for Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features
Viaarxiv icon

HASA-net: A non-intrusive hearing-aid speech assessment network

Nov 10, 2021
Hsin-Tien Chiang, Yi-Chiao Wu, Cheng Yu, Tomoki Toda, Hsin-Min Wang, Yih-Chun Hu, Yu Tsao

Figure 1 for HASA-net: A non-intrusive hearing-aid speech assessment network
Figure 2 for HASA-net: A non-intrusive hearing-aid speech assessment network
Figure 3 for HASA-net: A non-intrusive hearing-aid speech assessment network
Figure 4 for HASA-net: A non-intrusive hearing-aid speech assessment network
Viaarxiv icon

Speech Enhancement-assisted Stargan Voice Conversion in Noisy Environments

Oct 19, 2021
Yun-Ju Chan, Chiang-Jen Peng, Syu-Siang Wang, Hsin-Min Wang, Yu Tsao, Tai-Shih Chi

Figure 1 for Speech Enhancement-assisted Stargan Voice Conversion in Noisy Environments
Figure 2 for Speech Enhancement-assisted Stargan Voice Conversion in Noisy Environments
Figure 3 for Speech Enhancement-assisted Stargan Voice Conversion in Noisy Environments
Figure 4 for Speech Enhancement-assisted Stargan Voice Conversion in Noisy Environments
Viaarxiv icon

Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion

Sep 08, 2021
Yi-Syuan Liou, Wen-Chin Huang, Ming-Chi Yen, Shu-Wei Tsai, Yu-Huai Peng, Tomoki Toda, Yu Tsao, Hsin-Min Wang

Figure 1 for Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion
Figure 2 for Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion
Figure 3 for Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion
Figure 4 for Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion
Viaarxiv icon

SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours

Aug 24, 2021
Yi-Wei Chen, Hung-Shin Lee, Yen-Hsing Chen, Hsin-Min Wang

Figure 1 for SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
Figure 2 for SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
Figure 3 for SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
Figure 4 for SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours
Viaarxiv icon

SVSNet: An End-to-end Speaker Voice Similarity Assessment Model

Jul 20, 2021
Cheng-Hung Hu, Yu-Huai Peng, Junichi Yamagishi, Yu Tsao, Hsin-Min Wang

Figure 1 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Figure 2 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Figure 3 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Figure 4 for SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
Viaarxiv icon