4 papers
Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction
Hermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness +1
While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during separation. Prior correction strate…
SWAN: World-Aware Adaptive Multimodal Networks for Runtime Variations
Jason Wu, Shir-Kang Scott Jin, Yuyang Yuan +4
Multimodal deep neural networks deployed in realistic environments must contend with runtime variations: changes in modality quality, overall input complexity, and available platfo…
Tracking without Seeing: Geospatial Inference using Encrypted Traffic from Distributed Nodes
Sadik Yagiz Yetim, Gaofeng Dong, Isaac-Neil Zanoria +5
Accurate observation of dynamic environments traditionally relies on synthesizing raw, signal-level information from multiple distributed sensors. This work investigates an alterna…
On the Efficiency and Robustness of Vibration-based Foundation Models for IoT Sensing: A Case Study
Tomoyoshi Kimura, Jinyang Li, Tianshi Wang +9
This paper demonstrates the potential of vibration-based Foundation Models (FMs), pre-trained with unlabeled sensing data, to improve the robustness of run-time inference in (a cla…