Wenxi Chen's picture

4 1 9

Wenxi Chen

worstchan

·

https://cwx-worst-one.github.io/

cwx-worst-one

AI & ML interests

understanding & generation in speech and audio

Recent Activity

new activity 9 days ago

worstchan/EAT-base_epoch30_pretrain:AttributeError: 'EAT' object has no attribute '_initialize_weights'

liked a dataset 20 days ago

stepfun-ai/StepEval-Audio-360

liked a dataset about 2 months ago

Insects/ContextSpeech

View all activity

Organizations

None yet

authored a paper 6 months ago

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training

Paper • 2412.15649 • Published Dec 20, 2024

authored a paper 8 months ago

SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs

Paper • 2410.09503 • Published Oct 12, 2024

authored a paper over 1 year ago

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer

Paper • 2401.03497 • Published Jan 7, 2024 • 1