notesum.ai

Published at November 26

Scaling Speech-Text Pre-training with Synthetic Interleaved Data

cs.CL
cs.SD
eess.AS

Released Date: November 26, 2024

Authors: Aohan Zeng1, Zhengxiao Du1, Mingdao Liu1, Lei Zhang, Shengmin Jiang2, Yuxiao Dong1, Jie Tang1

Aff.: 1Tsinghua University; 2Zhipu.AI

Arxiv: http://arxiv.org/abs/2411.17607v1