Liumeng Xue

Postdoc@Hong Kong University of Science and Technology·中国·OpenReview

研究方向

speech generation · speech synthesis · sound generation · audio generation · speech and audio understanding · singing synthesis · singing voice conversion · voice conversion

7.0

Audio-FLAN: An Instruction-Following Dataset for Unified Understanding and Generation of Speech, Music, and Sound

合作者 (20)

Liumeng Xue

AudioX: A Unified Framework for Anything-to-Audio Generation

YuE: Scaling Open Foundation Models for Long-Form Music Generation

PodEval: A Multimodal Evaluation Framework for Podcast Audio Generation

Audio-FLAN: An Instruction-Following Dataset for Unified Understanding and Generation of Speech, Music, and Sound