Kai Yu

Fudan University — China

Computer Science · Physical Sciences

45h-index11.2kcitations503works2.62yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Speech Recognition and Synthesis(208), Speech and Audio Processing(140), Topic Modeling(136), Natural Language Processing Techniques(129), Music and Audio Processing(125)

Publications503 total

Trade-offs between disease label and treatment options: The case of low risk papillary thyroid cancer
Patient Education and Counseling·2026
Association of physical activity and hip fracture in chinese middle-aged and older adults: a prospective cohort study
The Aging Male·2025Open Access
Hydrochemical Characterization and RiskImplications of Sandstone Fissure Waterin Qianyingzi Coal Mine, China: Insightsfor Sustainable Resource Management
Polish Journal of Environmental Studies·2025Open Access
A Survey on Speech Large Language Models for Understanding
IEEE Journal of Selected Topics in Signal Processing·2025
TPS-Bench: Evaluating AI Agents' Tool Planning \& Scheduling Abilities in Compounding Tasks
arXiv (Cornell University)·2025Open Access
Pseudo-Autoregressive Neural Codec Language Models for Efficient Zero-Shot Text-to-Speech Synthesis
2025
Sedimentary response to Jurassic intracontinental orogenic process in Qinling Orogenic Belt: New insights from detrital zircon geochronology and heavy minerals in the Northeastern Sichuan Basin, SW China
Palaeogeography Palaeoclimatology Palaeoecology·2025
FOXO1-NMNAT3 axis dysregulation promotes doxorubicin cardiotoxicity: NAD <sup>+</sup> replenishment as a redox-targeted antioxidant therapy
Redox Report·2025Open Access
MULTI: multimodal understanding leaderboard with text and images
Science China Information Sciences·2025
Cross-Lingual F5-TTS: Towards Language-Agnostic Voice Cloning and Speech Synthesis
arXiv (Cornell University)·2025Open Access
VietASR: Achieving Industry-level Vietnamese ASR with 50-hour labeled data and Large-Scale Speech Pretraining
2025
Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling
2025
Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate
2025· 2 cited
Joint decoding method for controllable contextual speech recognition based on Speech LLM
arXiv (Cornell University)·2025Open Access
Impact of Repeated Impulse Voltage on the Breakdown and Space Charge Characteristics of Polypropylene for High-Voltage Cable Insulation
2025
News stance analysis based on word embedding similarity measure
IET conference proceedings.·2025
Research on Tennis Match Outcome Prediction Based on Multi-Algorithm Integration and Bayesian Analysis
Highlights in Science Engineering and Technology·2025Open Access
Convolutional Self-Attention Network with Disentangled Intents for Course Sequence Recommendation
2025
Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy
arXiv (Cornell University)·2025Open Access
Improving estimation of winter wheat biophysical traits using solar-induced fluorescence indices and a multi-task Gaussian process model
2025Open Access
page 1 of 26Next →

Frequent Co-authors

Yanmin Qian(19), Su Zhu(9), Steve Young(8), Milica Gašić(7), Simon Keizer(6), François Mairesse(6), Blaise Thomson(6), Heinrich Dinkel(6), Tian Tan(5), Nanxin Chen(5), Shuai Wang(5), Filip Jurčíček(5), Ruisheng Cao(3), Zhi Chen(3), Yanbin Zhao(3), Mengyue Wu(3), Mengxiao Bi(2), B. Thomson(2), S.J. Young(2), Xuankai Chang(2)