影响力指数

11.7/100

超过 36.2%

全站排名 #41,051

发表论文4 篇

平均评分5.0

年均产出2.0 篇/年

Jiawei Chen

Researcher@ByteDance Inc.·中国·OpenReview

研究方向

Singing Voice Synthesis · Large Language Model · Text to Speech

DiSTAR: Diffusion over a Scalable Token Autoregressive Representation for Speech Generation

ICLR 2026Rejected

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

ICML 2025Poster

Sounding that Object: Interactive Object-Aware Image to Audio Generation

ICML 2025Poster

Object-Aware Audio-Visual Sound Generation

ICLR 2025Withdrawn

合作者 (17)

Gopala Anumanchipalli