Search Results for author:
Found 10 papers, 6 papers with code
Similarity-Based Unsupervised Spelling Correction Using BioWordVec: Development and Usability Study of Bacterial Culture and Antimicrobial Susceptibility Reports
Conclusions: This tool corrected spelling errors effectively in the absence of a dictionary based on bacterial identification words in bacterial culture and antimicrobial susceptibility reports.
Cultural Vocal Bursts Intensity Prediction
Spelling Correction
TRACER: Extreme Attention Guided Salient Object Tracing Network
Existing studies on salient object detection (SOD) focus on extracting distinct objects with edge information and aggregating multi-level features to improve SOD performance.
Ranked #3 on
RGB Salient Object Detection
on HKU-IS
COMMA: Propagating Complementary Multi-Level Aggregation Network for Polyp Segmentation
In contrast to existing methods, we focus on propagating complementary information such that the complementary low-level explicit boundary with abstracted high-level representations diminishes the discrepancy.
Ranked #13 on
Medical Image Segmentation
on ETIS-LARIBPOLYPDB
MANNER: Multi-view Attention Network for Noise Erasure
In the field of speech enhancement, time domain methods have difficulties in achieving both high performance and efficiency.
Ranked #8 on
Speech Enhancement
on VoiceBank + DEMAND
Multi-View Attention Transfer for Efficient Speech Enhancement
In this study, we propose multi-view attention transfer (MV-AT), a feature-based distillation, to obtain efficient speech enhancement models in the time domain.
Ranked #14 on
Speech Enhancement
on VoiceBank + DEMAND
GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentation
Different from the existing studies, this study aims to reduce the epistemic uncertainty measured by the entropy for a precise semantic segmentation.
TriAAN-VC: Triple Adaptive Attention Normalization for Any-to-Any Voice Conversion
The existing methods do not simultaneously satisfy the above two aspects of VC, and their conversion outputs suffer from a trade-off problem between maintaining source contents and target characteristics.
AD-YOLO: You Look Only Once in Training Multiple Sound Event Localization and Detection
Hence, the format enables the model to handle the polyphony problem, regardless of the number of sound overlaps.
MetricGAN-OKD: Multi-Metric Optimization of MetricGAN via Online Knowledge Distillation for Speech Enhancement
In speech enhancement, MetricGAN-based approaches reduce the discrepancy between the $L_p$ loss and evaluation metrics by utilizing a non-differentiable evaluation metric as the objective function.
Ranked #7 on
Speech Enhancement
on VoiceBank + DEMAND
Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer
In this paper, we propose a simple transfer learning scheme that maintains input patch sizes, unlike previous methods, to avoid input discrepancies.
Ranked #5 on
Audio captioning
on AudioCaps
