Xiaodong Cui

Shandong University of Science and Technology — China

Computer Science · Physical Sciences

28h-index2.7kcitations145works1.22yr 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(95), Speech and Audio Processing(76), Music and Audio Processing(59), Natural Language Processing Techniques(19), Advanced Neural Network Applications(13)

Publications145 total

Multiscale feature fusion analysis of multibeam and side-scan sonar for seafloor sediment classification in shallow reef environments
International Journal of Remote Sensing·2026
A Hybrid CUBE-IForest Approach for Outlier Detection in Multibeam Bathymetry
Journal of Marine Science and Engineering·2026Open Access
SEER: Semantic Enhancement and Emotional Reasoning Network for Multimodal Fake News Detection
2025
Complete genome sequence of <i>Robbsia andropogonis</i> strain FG-1 causing bacterial leaf spot disease on <i>Pueraria montana</i> var. <i>thomsonii</i> in China
Microbiology Resource Announcements·2025Open Access
BiRQ: Bi-Level Self-Labeling Random Quantization for Self-Supervised Speech Recognition
arXiv (Cornell University)·2025Open Access
Heterogeneous Self-Supervised Acoustic Pre-Training with Local Constraints
arXiv (Cornell University)·2025Open Access
Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities
ArXiv.org·2025· 1 citedOpen Access
Associations Between the Atherogenic Index of Plasma and Triglyceride-Glucose Index With Coronary Microvascular Dysfunction in Hypertensive Patients
Diabetes Metabolic Syndrome and Obesity·2025· 3 citedOpen Access
Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition
IEEE Transactions on Audio Speech and Language Processing·2024· 1 cited
Bilevel Joint Unsupervised and Supervised Training for Automatic Speech Recognition
arXiv (Cornell University)·2024Open Access
Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
arXiv (Cornell University)·2024Open Access
The relative and combined ability of triglyceride-glucose index and stress hyperglycemia ratio to predict major adverse cardio-cerebral events in patients with multivessel coronary artery disease
Diabetology & Metabolic Syndrome·2024· 3 citedOpen Access
M2ASR: Multilingual Multi-task Automatic Speech Recognition via Multi-objective Optimization
2024· 1 cited
How Can Personalized Context Help? Exploring Joint Retrieval of Passage and Personalized Context
2024
Reparameterization Head for Efficient Multi-Input Networks
2024· 7 cited
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
2024· 4 cited
How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
arXiv (Cornell University)·2024· 1 citedOpen Access
Seabed sediment classification based on topography-based image partitioning: a case study from the southern Irish Sea
2024· 1 cited
Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
arXiv (Cornell University)·2024Open Access
Soft Random Sampling: A Theoretical and Empirical Analysis
arXiv (Cornell University)·2023Open Access
page 1 of 8Next →

Frequent Co-authors

Brian Kingsbury(14), Michael Picheny(11), George Saon(8), Bhuvana Ramabhadran(7), Jia Cui(6), Abhinav Sethy(6), Lidia Mangu(6), Ulrich Finkler(6), Xiao Sun(5), Naigang Wang(5), Swagath Venkataramani(5), Abeer Alwan(5), David S. Kung(5), Vaibhava Goel(4), Chia‐Yu Chen(4), Zoltán Tüske(4), Jonathan Mamou(4), Kailash Gopalakrishnan(3), Vijayalakshmi Srinivasan(3), Ralf Schlüter(3)