3 citations · 5 across the 7 of their papers we have counts for
7 papers
D4AM: A General Denoising Framework for Downstream Acoustic Models
Chi-Chang Lee, Yu Tsao, Hsin-Min Wang +1
The performance of acoustic models degrades notably in noisy environments. Speech enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition (ASR) sys…
Globally Consistent Video Depth and Pose Estimation with Efficient Test-Time Training
Yao-Chih Lee, Kuan-Wei Tseng, Guan-Sheng Chen +1
Dense depth and pose estimation is a vital prerequisite for various video applications. Traditional solutions suffer from the robustness of sparse feature tracking and insufficient…
NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling
Chi-Chang Lee, Cheng-Hung Hu, Yu-Chen Lin +3
For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous nois…
Continual Learning for Visual Search with Backward Consistent Feature Embedding
Timmy S. T. Wan, Jun-Cheng Chen, Tzer-Yi Wu +1
In visual search, the gallery set could be incrementally growing and added to the database in practice. However, existing methods rely on the model trained on the entire dataset, i…
STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing
Wen-Cheng Chen, Min-Chun Hu, Chu-Song Chen
Geometry-aware modules are widely applied in recent deep learning architectures for scene representation and rendering. However, these modules require intrinsic camera information…
Part-Aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking
Hau Chu, Jia-Hong Lee, Yao-Chih Lee +3
This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multi-view. The main challenge lies in finding the cross-view and temporal cor…
Video-based Person Re-identification without Bells and Whistles
Chih-Ting Liu, Jun-Cheng Chen, Chu-Song Chen +1
Video-based person re-identification (Re-ID) aims at matching the video tracklets with cropped video frames for identifying the pedestrians under different cameras. However, there…