Cite
Notes
Only stored in your browser.
Attribution
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
arXiv 2025
EAT: Self-Supervised Pre-Training with Efficient Audio Transformer
arXiv 2024
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training
from 3 papers
Wenxi Chen
Xie Chen
professor
Ziyang Ma
Kai Yu
Ruiyang Xu
Xiquan Li
Yanqiao Zhu
Zhikang Niu
Zhisheng Zheng
Chen Yang