Tootfinder

Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
Yanfan Du, Jun Zhang, Bin Wang, Jin Qiu, Lu Huang, Yuan Ge, Xiaoqian Liu, Tong Xiao, Jingbo Zhu
https://arxiv.org/abs/2508.18701

Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System
Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neologisms remains challenging. To address this, we propose Attention2Probability: attention-driven terminology probability estimation for robust speech-to-text system, which is lightweight, flexible, and accurate. Attention2Probability converts cross-attention weights between speech and terminology into presence probabili…

Beating solitons with nonzero relative wavenumber, their interaction, and coexistence with Akhmediev breathers
Wen-Juan Che, Chong Liu
https://arxiv.org/abs/2506.16989

Beating solitons with nonzero relative wavenumber, their interaction, and coexistence with Akhmediev breathers
We study beating solitons and their interaction for the three-component nonlinear Schrödinger equations (NLSEs) in both focusing and defocusing cases. We identify a previously unknown family of beating solitons with nonzero relative wavenumber which is absent in the two-component NLSEs. Existence diagrams of these beating solitons are extracted from the exact solutions. Unique coexistence and interaction between beating solitons and vector Akhmediev breathers are revealed by using the existenc…