3 papers
cs.SD2025
OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
Xuelong Geng, Kun Wei, Qijie Shao +18
Large Language Models (LLMs) have made significant progress in various downstream tasks, inspiring the development of Speech Understanding Language Models (SULMs) to enable compreh…
eess.SP2025
Subject Disentanglement Neural Network for Speech Envelope Reconstruction from EEG
Li Zhang, Jiyao Liu
Reconstructing speech envelopes from EEG signals is essential for exploring neural mechanisms underlying speech perception. Yet, EEG variability across subjects and physiological a…
cs.SD2025
Adaptive Data Augmentation with NaturalSpeech3 for Far-field Speaker Verification
Li Zhang, Jiyao Liu, Lei Xie
The scarcity of speaker-annotated far-field speech presents a significant challenge in developing high-performance far-field speaker verification (SV) systems. While data augmentat…