Keqi Deng

Institute of Technology of Cambodia — KH

Computer Science · Physical Sciences

9h-index246citations49works2.22yr 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(33), Natural Language Processing Techniques(26), Music and Audio Processing(14), Topic Modeling(12), Speech and Audio Processing(9)

Publications49 total

MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages
arXiv (Cornell University)·2025Open Access
Multi-head Temporal Latent Attention
arXiv (Cornell University)·2025Open Access
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
arXiv (Cornell University)·2025Open Access
A smart electroelastomer cylindrical soft robot
Journal of Physics Conference Series·2025Open Access
Hierarchical Crack Engineering-Enabled High-Linearity and Ultrasensitive Strain Sensors
Scholar Commons (University of South Carolina)·2025
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
2025
Hierarchical Crack Engineering-Enabled High-Linearity and Ultrasensitive Strain Sensors
ACS Sensors·2025· 14 cited
Hollow Fiber-Based Strain Sensors with Desirable Modulus and Sensitivity at Effective Deformation for Dexterous Electroelastomer Cylindrical Actuator
Scholar Commons (University of South Carolina)·2025Open Access
Hollow fiber-based strain sensors with desirable modulus and sensitivity at effective deformation for dexterous electroelastomer cylindrical actuator
Microsystems & Nanoengineering·2025· 1 citedOpen Access
Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning
2025Open Access
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
2025· 21 cited
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation
2025Open Access
Wav2Prompt: End-to-End Speech Prompt Learning and Task-based Fine-tuning for Text-based LLMs
2025· 2 citedOpen Access
Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition
arXiv (Cornell University)·2024Open Access
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
arXiv (Cornell University)·2024· 1 citedOpen Access
Reinforced Magnetic‐Responsive Electro‐Ionic Artificial Muscles by 3D Laser‐Induced Graphene Nano‐Heterostructures
Advanced Materials·2024· 7 citedOpen Access
Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning
arXiv (Cornell University)·2024Open Access
Highly sensitive and chemically resistant moisture sensor based on polyether sulfone and polyimide composite membrane for power transformer oil
Journal of Physics Conference Series·2024Open Access
Decoupled structure for improved adaptability of end-to-end models
Speech Communication·2024· 3 citedOpen Access
Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation
arXiv (Cornell University)·2024Open Access
page 1 of 3Next →

Frequent Co-authors

Philip C. Woodland(19), Gaofeng Cheng(9), Dezhi Wu(8), Songjun Cao(6), Yonghong Yan(6), Pengyuan Zhang(5), Yike Zhang(4), Shinji Watanabe(4), Ziyang Ma(4), Xie Chen(4), Zhenjin Xu(4), Li Ta(3), Yang Zhang(3), Lida Xu(3), Lianjie Lu(3), Yexing Du(3), Xie Chen(3), Long Ma(2), Long Ma(2), Zehui Yang(2)