Kaizhi Qian

7

Papers

15

Total Citations

Papers (7)

UniMuMo: Unified Text, Music, and Motion Generation

RapVerse: Coherent Vocals and Whole-Body Motion Generation from Text

Speech Self-Supervised Learning Using Diffusion Model Synthetic Data

Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling

Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos

PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition

NeurIPS 2021arXiv

Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing

NeurIPS 2022arXiv