Cite
Notes
Only stored in your browser.
Attribution
OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia
arXiv 2025
Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought
Autoregressive Speech Synthesis with Next-Distribution Prediction
arXiv 2024
from 3 papers
Lei Xie
Xinfa Zhu
Shuiyuan Wang
Xuelong Geng
Zhixian Zhao
Chengyou Wang
Guojian Li
Kun Wei
Li Zhang
Mingchen Shao