Get started
Author

Yu Xi

Observed name: Xi, Yu
ORCID: 0000-0003-0498-0328
Observed ORCID: 0000-0003-0498-0328
OpenAlex ID: A5103250176
Contrastive Learning with Audio Discrimination for Customizable Keyword Spotting in Continuous Speech
2024 · Yu Xi, Baochen Yang, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 16
PDF
Transmission Line Insulator Defect Detection Based on Swin Transformer and Context
2023 · Yu Xi, Ke Zhou, et al. · Machine Intelligence Research · 14
Text Adaptive Detection for Customizable Keyword Spotting
2022 · Yu Xi, Tian Tan, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 13
Text-aware Speech Separation for Multi-talker Keyword Spotting
2024 · Haoyu Li, Baochen Yang, et al. · Interspeech (USB) · 9
PDF
TDT-KWS: Fast and Accurate Keyword Spotting Using Token-and-Duration Transducer
2024 · Yu Xi, Hao Li, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 9
PDF
NTC-KWS: Noise-aware CTC for Robust Keyword Spotting
2025 · Yu Xi, Haoyu Li, et al. · IEEE International Conference on Acoustics Speech and Signal Processing · 8
PDF
Qwen3-ASR Technical Report
2026 · Shi, Xian, Wang, Xiong, et al. · arXiv (Cornell University) · 1
PDF
Detect, Attend and Extract: Keyword Guided Target Speaker Extraction
2026 · Haoyu Li, Yu Xi, et al. · International Joint Conference on Artificial Intelligence
PDF
DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios
2026 · Mu, Bingshen, Shi, Xian, et al. · arXiv (Cornell University)
PDF
A Unified and Reproducible Experimentation Framework for Speech Understanding
2026 · Peng, Jing, Du, Junhao, et al. · arXiv (Cornell University)
PDF
TASU: Text-only Alignment for Speech Understanding
2026 · Jing Peng, Yi Yang, et al. · IEEE International Conference on Acoustics Speech and Signal Processing
TASU2: Controllable CTC Simulation for Alignment and Low-Resource Adaptation of Speech LLMs
2026 · Peng, Jing, Wang, Chenghao, et al. · arXiv (Cornell University)
PDF
TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
2026 · She, Qingshun, Peng, Jing, et al. · arXiv (Cornell University)
PDF
HoliTok: A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
2026 · Bohan Li, Lianshi, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
End-to-End Streaming Customizable Keyword Spotting Based on Text-Adaptive Neural Search
2024 · Baochen Yang, Jiaqi Guo, et al. · Communications in computer and information science
Works count: 15
Citation count: 70
H-index: 6
I10-index: 3
Year
Topic
Type