Taiha Li

Detach and Enhance: Learning Disentangled Cross-modal Latent Representation for Efficient Face-Voice Association and Matching

Nan Wang, Y. Cheung, Xin Liu, 2022, 2022 IEEE International Conference on Data Mining (ICDM).

Disentangling Prosody Representations with Unsupervised Speech Reconstruction

C. Weber, S. Wermter, F. Ren, 2022, ArXiv.

Data Augmentation with Unsupervised Speaking Style Transfer for Speech Emotion Recognition

C. Weber, S. Wermter, Wei Wang, 2022, ArXiv.

FastBCSD: Fast and Efficient Neural Network for Binary Code Similarity Detection

Guibo Zhu, Che-Wei Huang, Taiha Li, 2023, ArXiv.

Disentangling Prosody Representations With Unsupervised Speech Reconstruction

C. Weber, S. Wermter, F. Ren, 2022, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Improving Speech Emotion Recognition with Unsupervised Speaking Style Transfer

C. Weber, S. Wermter, Wei Wang, 2022, 2211.08843.