Zeqian Ju

Computer Science · Physical Sciences

10h-index433citations25works2.72yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Topic Modeling(11), Music and Audio Processing(11), Natural Language Processing Techniques(7), Speech Recognition and Synthesis(7), Speech and Audio Processing(6)

Publications25 total

HeartMuLa: A Family of Open Sourced Music Foundation Models
arXiv (Cornell University)·2026Open Access
HeartMuLa: A Family of Open Sourced Music Foundation Models
ArXiv.org·2026Open Access
FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation
2025
ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling
arXiv (Cornell University)·2025Open Access
Kimi-Audio Technical Report
arXiv (Cornell University)·2025Open Access
ALMTokenizer: A Low-bitrate and Semantic-rich Audio Codec Tokenizer for Audio Language Modeling
arXiv (Cornell University)·2025Open Access
FlashSpeech: Efficient Zero-Shot Speech Synthesis
2024· 5 cited
FlashSpeech: Efficient Zero-Shot Speech Synthesis
arXiv (Cornell University)·2024· 1 citedOpen Access
RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis
arXiv (Cornell University)·2024· 2 citedOpen Access
NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
arXiv (Cornell University)·2024· 19 citedOpen Access
PromptTTS 2: Describing and Generating Voices with Text Prompt
arXiv (Cornell University)·2023Open Access
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
arXiv (Cornell University)·2023· 37 citedOpen Access
AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models
arXiv (Cornell University)·2023· 9 citedOpen Access
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method
2022· 16 citedOpen Access
TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method
arXiv (Cornell University)·2021· 7 citedOpen Access
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
arXiv (Cornell University)·2021· 10 citedOpen Access
MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training
2021· 87 citedOpen Access
On the Generation of Medical Dialogs for COVID-19
2021· 16 citedOpen Access
On the Generation of Medical Dialogues for COVID-19
2020· 15 citedOpen Access
On the Generation of Medical Dialogues for COVID19
2020· 5 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Pengtao Xie(8), Shu Chen(7), Tao Qin(7), Guangtao Zeng(6), Wenmian Yang(6), Xuehai He(6), Bowen Tan(5), Subrato Chakravorty(5), Xingyi Yang(5), Qingyang Wu(5), Eric P. Xing(5), Meng Zhou(4), Rui Wang(4), Yue Yang(3), Sicheng Wang(3), Jiaqi Zeng(3), Xiangyu Dong(3), Hongchao Fang(3), Penghui Zhu(3), Xu Tan(3)