arXiv Machine Learning By Jakob Kienegger, Tal Peer, Sina Khanagha, Timo Gerkmann

Weakly Guided and Autoregressive Beamformer Parameterization for Generalizable Moving Speaker Extraction in Higher-Order Ambisonics

Read the original on arXiv Machine Learning →

arXiv:2607. 04471v1 Announce Type: cross Abstract: Linear spatial filters (beamformers) enable robust, generalizable and interpretable speech enhancement with performance guarantees under ideal parameterization.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Jul 16

A Hybrid Mamba for Audio-Visual Navigation

arXiv:2607. 13110v1 Announce Type: cross Abstract: Since the paradigm centered on convolutional neural networks and recurrent architectures was established in 2020, the fundamental backbone networks for audio-visual navigation have undergone no essential changes for more than five years, making them inadequate to support efficient representation of dynamic multimodal sequences.

By Yi Wang, Yinfeng Yu