Statistical Analysis of Randomness in Training of Small-Scale Neural Networks for Speech Enhancement
Briegleb A, Kellermann W (2022)
Publication Language: English
Publication Type: Conference contribution, Original article
Publication year: 2022
Event location: Bamberg
URI: https://ieeexplore.ieee.org/document/9914739
DOI: 10.1109/IWAENC53105.2022.9914739
Abstract
For the training of neural networks, randomness due to the initialization is a widely acknowledged factor for training success. In speech enhancement, randomness is also introduced via the creation of the training dataset due to the synthetic mixing of speech and noise, and other data augmentation techniques. This aspect of randomness is often neglected in literature. In this contribution, we quantify the effect of randomness in the generation of the training dataset in comparison to the randomness introduced by the network initialization and find that for small networks and very small datasets, the assembly of the training dataset has a significant influence on the network’s performance.
Authors with CRIS profile
How to cite
APA:
Briegleb, A., & Kellermann, W. (2022). Statistical Analysis of Randomness in Training of Small-Scale Neural Networks for Speech Enhancement. In IEEE (Eds.), Proceedings of the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC). Bamberg, DE.
MLA:
Briegleb, Annika, and Walter Kellermann. "Statistical Analysis of Randomness in Training of Small-Scale Neural Networks for Speech Enhancement." Proceedings of the 2022 International Workshop on Acoustic Signal Enhancement (IWAENC), Bamberg Ed. IEEE, 2022.
BibTeX: Download