3 papers
cs.CL2025
MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
Xingjian Zhao, Zhe Xu, Qinyuan Cheng +20
Spoken dialogue systems often rely on cascaded pipelines that transcribe, process, and resynthesize speech. While effective, this design discards paralinguistic cues and limits exp…
cs.SD2025
HDA-SELD: Hierarchical Cross-Modal Distillation with Multi-Level Data Augmentation for Low-Resource Audio-Visual Sound Event Localization and Detection
Qing Wang, Ya Jiang, Hang Chen +3
This work presents HDA-SELD, a unified framework that combines hierarchical cross-modal distillation (HCMD) and multi-level data augmentation to address low-resource audio-visual (…
cs.SD2025
An Experimental Study on Joint Modeling for Sound Event Localization and Detection with Source Distance Estimation
Yuxuan Dong, Qing Wang, Hengyi Hong +2
In traditional sound event localization and detection (SELD) tasks, the focus is typically on sound event detection (SED) and direction-of-arrival (DOA) estimation, but they fall s…