Cite
Notes
Only stored in your browser.
Attribution
EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting
arXiv 2025
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
from 2 papers
Chen Yang
Guanrou Yang
Wenxi Chen
Xie Chen
professor
Zhikang Niu
Ziyang Ma
Emmanouil Benetos
Eng Siong Chng
Fan Yu
Haina Zhu