7 papers · 1 filter
AcousticAgent: A Floorplan-Centric Simulation Platform for Distributed Multi-Room Speech Processing
Zhiqi Ai, Han Cheng, Shiyi Mu +2
Existing acoustic simulation tools either generate room impulse responses (RIRs) efficiently in parameterized rooms or rely on preconstructed three-dimensional scenes, making it di…
PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs
Zhiqi Ai, Han Cheng, Shiyi Mu +2
Contextual biasing improves rare-word recognition in speech large language models (SpeechLLMs), but efficiently exploiting large bias lists remains challenging. We propose PTC-Bias…
Physics-Informed WiFi Sensing for Robust 3D Human Pose Estimation in Mobile and Cross-Environment Settings
Kaixuan Huang, Yuanbo Chen, Guangjin Pan +4
Device-free human pose estimation using commodity WiFi signals has emerged as a promising paradigm for pervasive sensing in mobile computing systems. However, existing approaches o…
LARAD: Layout-Aware Road Anomaly Detection via Spatial-Logic Reasoning
Shiyi Mu, Xujie Chen, Shugong Xu
Accurate open-world obstacle detection is critical for autonomous driving. Current anomaly segmentation methods suffer from a fundamental blind spot: they over-rely on texture nove…
DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detection
Shiyi Mu, Zichong Gu, Zhiqi Ai +2
Stereo-based 3D obstacle perception for autonomous driving is currently constrained by an imbalanced triplet: deployment cost, detection accuracy, and open-set adaptability. While…
Stabilizing Short Duration Speaker Verification through Neural Re-scoring with Hybrid Enrollment
Zhiqi Ai, Han Cheng, Shiyi Mu +3
Short-duration speaker verification (SDSV) is crucial for personalized keyword spotting, where test utterances are typically shorter than three seconds. Limited speech duration res…
Effective User-defined Keyword Spotting with Dual-stage Matching, Multi-modal Enrollment, and Continual Adaptation
Zhiqi Ai, Han Cheng, Shiyi Mu +3
User-defined keyword spotting (KWS) is crucial for personalized voice interaction, yet existing methods face several challenges: (1) insufficient discriminability among confusable…