79 citations · 377 across the 61 of their papers we have counts for
61 papers
Conditional Pseudo-Supervised Contrast for Data-Free Knowledge Distillation
Renrong Shao, Wei Zhang, Jun wang
Data-free knowledge distillation~(DFKD) is an effective manner to solve model compression and transmission restrictions while retaining privacy protection, which has attracted exte…
Music2Fail: Transfer Music to Failed Recorder Style
Chon In Leong, I-Ling Chung, Kin-Fong Chao +3
The goal of music style transfer is to convert a music performance by one instrument into another while keeping the musical contents unchanged. In this paper, we investigate anothe…
Improving Real-Time Music Accompaniment Separation with MMDenseNet
Chun-Hsiang Wang, Chung-Che Wang, Jun-You Wang +2
Music source separation aims to separate polyphonic music into different types of sources. Most existing methods focus on enhancing the quality of separated results by using a larg…
Adapting pretrained speech model for Mandarin lyrics transcription and alignment
Jun-You Wang, Chon-In Leong, Yu-Chen Lin +2
The tasks of automatic lyrics transcription and lyrics alignment have witnessed significant performance improvements in the past few years. However, most of the previous works only…
GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models
Hanjing Wang, Man-Kit Sit, Congjie He +5
This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transf…
MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models
Yidong Liu, FuKai Shang, Fang Wang +5
With the advancement of deep learning technologies, general-purpose large models such as GPT-4 have demonstrated exceptional capabilities across various domains. Nevertheless, ther…