no code implementations • 15 Jan 2024 • William Watkins, Heehwan Wang, Sangyoon Bae, Huan-Hsin Tseng, Jiook Cha, Samuel Yen-Chi Chen, Shinjae Yoo
The utility of machine learning has rapidly expanded in the last two decades and presents an ethical challenge.
no code implementations • 23 Oct 2023 • Tyler Wang, Huan-Hsin Tseng, Shinjae Yoo
A major concern of deep learning models is the large amount of data that is required to build and train them, much of which is reliant on sensitive and personally identifiable information that is vulnerable to access by third parties.
no code implementations • 10 Oct 2023 • Rod Rofougaran, Shinjae Yoo, Huan-Hsin Tseng, Samuel Yen-Chi Chen
The preservation of privacy is a critical concern in the implementation of artificial intelligence on sensitive training data.
no code implementations • 8 Sep 2023 • Xi Yu, Huan-Hsin Tseng, Shinjae Yoo, Haibin Ling, Yuewei Lin
Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information.
2 code implementations • 28 Mar 2023 • Dmitrii Torbunov, Yi Huang, Huan-Hsin Tseng, Haiwang Yu, Jin Huang, Shinjae Yoo, MeiFeng Lin, Brett Viren, Yihui Ren
An unpaired image-to-image (I2I) translation technique seeks to find a mapping between two domains of data in a fully unsupervised manner.
1 code implementation • 3 Feb 2023 • Huan-Hsin Tseng, Hsin-Yi Lin, Kuo-Hsuan Hung, Yu Tsao
The method shows an increase in efficiency and accuracy for domain adaptation.
no code implementations • 11 Nov 2022 • Hsin-Yi Lin, Huan-Hsin Tseng, Yu Tsao
It has been shown recently that deep learning based models are effective on speech quality prediction and could outperform traditional metrics in various perspectives.
1 code implementation • 7 Apr 2022 • Kuo-Hsuan Hung, Szu-Wei Fu, Huan-Hsin Tseng, Hsin-Tien Chiang, Yu Tsao, Chii-Wann Lin
We further study the relationship between the noise robustness of SSL representation via clean-noisy distance (CN distance) and the layer importance for SE.
Ranked #8 on Speech Enhancement on VoiceBank + DEMAND
no code implementations • 5 Dec 2021 • Heng-Cheng Kuo, Yu-Peng Hsieh, Huan-Hsin Tseng, Chi-Te Wang, Shih-Hau Fang, Yu Tsao
Conclusion: By deploying factorized convolutional neural networks and domain adversarial training, domain-invariant features can be derived for voice disorder classification with limited resources.
1 code implementation • NeurIPS 2021 • Hsin-Yi Lin, Huan-Hsin Tseng, Xugang Lu, Yu Tsao
This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing.
no code implementations • 7 Dec 2020 • Tsai-Min Chen, Yuan-Hong Tsai, Huan-Hsin Tseng, Kai-Chun Liu, Jhih-Yu Chen, Chih-Han Huang, Guo-Yuan Li, Chun-Yen Shen, Yu Tsao
In our experiments, we downsampled the ECG signals from the CPSC2018 dataset and evaluated their HMC accuracies with and without the SRECG.