Get started
Author

Zheqi Dai

Observed name: Dai, Zheqi
Observed institution: Chinese University of Hong Kong
OpenAlex ID: A5102690985
Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
2025 · Zhen Ye, Peiwen Sun, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 20
PDF
Music Source Restoration
2025 · Yongyi Zang, Zheqi Dai, et al. · IEEE International Workshop on Multimedia Signal Processing (MMSP) · 5
PDF
Summary of the Inaugural Music Source Restoration Challenge
2026 · Yongyi Zang, Jiarui Hai, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 2
MusicScore: A Dataset for Music Score Modeling and Generation
2024 · Lin, Yuheng, Dai, Zheqi, et al. · arXiv (Cornell University) · 1
PDF
High-Fidelity Song Generation with Joint Discrete and Continuous Modeling
2026 · Dai, Zheqi, Wu, Zhiyue, et al. · arXiv (Cornell University)
PDF
HMU-Bench: Hierarchical Music Understanding Benchmark for Omni Models
2026 · Dai, Zheqi, Wang, Boyang, et al. · arXiv (Cornell University)
PDF
OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue
2026 · He, Haolin, Chu, Yunfei, et al. · arXiv (Cornell University)
PDF
StepAudio 3 Gen Technical Report
2026 · Lin, Bin, Zhao, Bo, et al. · arXiv (Cornell University)
PDF
StepAudio 3 Music Technical Report
2026 · Feng, Chengli, Wu, Zhiyue, et al. · arXiv (Cornell University)
PDF
Summary of DCASE 2026 Task 5: Audio-Dependent Question Answering
2026 · He, Haolin, Sun, Renhe, et al. · arXiv (Cornell University)
PDF
One-Step Token-to-Waveform Generation with MeanFlow in Latent Space
2026 · Dai, Zheqi, Zhang, Guangyan, et al. · arXiv (Cornell University)
PDF
Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation
2026 · Ye, Zhen, Tan, Xu, et al. · arXiv (Cornell University)
PDF
ISSE: An Instruction-Guided Speech Style Editing Dataset and Benchmark
2026 · Yun Chen, Qi Chen, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
PDF
ARCHI-TTS: A Flow-Matching-Based Text-to-Speech Model with Self-Supervised Semantic Aligner and Accelerated Inference
2026 · Chunyat Wu, Jiajun Deng, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated Inference
2026 · Wu, Chunyat, Deng, Jiajun, et al. · arXiv (Cornell University)
PDF
SemanticAudio: Audio Generation and Editing in Semantic Space
2026 · Dai, Zheqi, Zhang, Guangyan, et al. · arXiv (Cornell University)
PDF
Summary of The Inaugural Music Source Restoration Challenge
2026 · Zang, Yongyi, Hai, Jiarui, et al. · Research Portal (King's College London)
Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis
2025 · Ye, Zhen, Zhu, Xinfa, et al. · arXiv (Cornell University)
PDF
PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain
2024 · Jianyi Chen, Zheqi Dai, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Works count: 21
Citation count: 28
H-index: 2
I10-index: 1
Year
Topic
Type