Follow
Ziyi Xu
Ziyi Xu
Ph.D. Student, TU Braunschweig
Verified email at ifn.ing.tu-bs.de - Homepage
Title
Cited by
Cited by
Year
Using separate losses for speech and noise in mask-based speech enhancement
Z Xu, S Elshamy, T Fingscheidt
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
122020
Components loss for neural networks in mask-based speech enhancement
Z Xu, S Elshamy, Z Zhao, T Fingscheidt
EURASIP Journal on Audio, Speech, and Music Processing 2021 (1), 1-20, 2021
92021
Deep noise suppression with non-intrusive pesqnet supervision enabling the use of real training data
Z Xu, M Strake, T Fingscheidt
arXiv preprint arXiv:2103.17088, 2021
82021
Improving convolutional recurrent neural networks for speech emotion recognition
P Meyer, Z Xu, T Fingscheidt
2021 IEEE Spoken Language Technology Workshop (SLT), 365-372, 2021
72021
Concatenated identical DNN (CI-DNN) to reduce noise-type dependence in DNN-based speech enhancement
Z Xu, M Strake, T Fingscheidt
2019 27th European Signal Processing Conference (EUSIPCO), 1-5, 2019
42019
On the effects of speaker gender in emotion recognition training data
Z Xu, P Meyer, T Fingscheidt
Speech Communication; 13th ITG-Symposium, 1-5, 2018
32018
A priori SNR estimation using discriminative non-negative matrix factorization
Z Xu, S Elshamy, T Fingscheidt
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
32018
Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet
Z Xu, M Strake, T Fingscheidt
IEEE/ACM Transactions on Audio, Speech, and Language Processing 30, 1572-1585, 2022
12022
Does a PESQNet (Loss) Require a Clean Reference Input? The Original PESQ Does, But ACR Listening Tests Don't
Z Xu, M Strake, T Fingscheidt
arXiv preprint arXiv:2205.02085, 2022
2022
The system can't perform the operation now. Try again later.
Articles 1–9