Briegleb A, Kellermann W (2024)
Publication Language: English
Publication Type: Conference contribution, Original article
Publication year: 2024
Pages Range: 907-911
Conference Proceedings Title: 2024 32nd European Signal Processing Conference (EUSIPCO)
Event location: Lyon, France
ISBN: 978-9-4645-9361-7
URI: https://ieeexplore.ieee.org/document/10715258
DOI: 10.48550/arXiv.2406.11376
Open Access Link: https://arxiv.org/abs/2406.11376
When using artificial neural networks for multichannel speech enhancement, filtering is often achieved by estimating a complex-valued mask that is applied to all or one reference channel of the input signal. The estimation of this mask is based on the noisy multichannel signal and, hence, can exploit spatial and spectral cues simultaneously. While it has been shown that exploiting spatial and spectral cues jointly is beneficial for the speech enhancement result, the mechanics of the interplay of the two inside the neural network are still largely unknown. In this contribution, we investigate how two conceptually different neural spatiospectral filters (NSSFs) exploit spatial cues depending on the training target signal and show that, while one NSSF always performs spatial filtering, the other one is selective in leveraging spatial information depending on the task at hand. These insights provide better understanding of the information the NSSFs use to make their prediction and, thus, allow to make informed decisions regarding their design and deployment.
APA:
Briegleb, A., & Kellermann, W. (2024). Spatially Constrained vs. Unconstrained Filtering in Neural Spatiospectral Filters for Multichannel Speech Enhancement. In European Association for Signal Processing (EURASIP) (Eds.), 2024 32nd European Signal Processing Conference (EUSIPCO) (pp. 907-911). Lyon, France.
MLA:
Briegleb, Annika, and Walter Kellermann. "Spatially Constrained vs. Unconstrained Filtering in Neural Spatiospectral Filters for Multichannel Speech Enhancement." Proceedings of the 2024 32nd European Signal Processing Conference (EUSIPCO), Lyon, France Ed. European Association for Signal Processing (EURASIP), 2024. 907-911.
BibTeX: Download