Tootfinder

Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition
Upasana Tiwari, Rupayan Chakraborty, Sunil Kumar Kopparapu
https://arxiv.org/abs/2510.09072

Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition
Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech emotion recognition models through improved representation learning. First, our model employs EDRL (Emotion-Disentangled Representation Learning) to extract class-specific discriminative features while preserving shared similarities across emotion categories. N…

Bin sehr traurig, nicht auf der #FORGE25 zu sein, aber froh, das Philipp Tögel unseren @… würdig vertritt. Wer direkt mal in unseren Ansatz für die TEI-Modellierung heterogener multilingualer Textkorpora reinschnuppern will:

Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement
Nikolai Lund K\"uhne, Jesper Jensen, Jan {\O}stergaard, Zheng-Hua Tan
https://arxiv.org/abs/2510.01958

Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancement
Recent advances in speech enhancement have shown that models combining Mamba and attention mechanisms yield superior cross-corpus generalization performance. At the same time, integrating Mamba in a U-Net structure has yielded state-of-the-art enhancement performance, while reducing both model size and computational complexity. Inspired by these insights, we propose RWSA-MambaUNet, a novel and efficient hybrid model combining Mamba and multi-head attention in a U-Net structure for improved cros…