Related papers: WhaleVAD-BPN: Improving Baleen Whale Call Detectio…

Voice recognition and speaker identification are vital for applications in security and personal assistants. This paper presents a lightweight 1D-Convolutional Neural Network (1D-CNN) designed to perform speaker identification on minimal…

Despite significant success of deep learning in object detection tasks, the standard training of deep neural networks requires access to a substantial quantity of annotated images across all classes. Data annotation is an arduous and…

Since the advent of Deep Learning (DL), Speech Enhancement (SE) models have performed well under a variety of noise conditions. However, such systems may still introduce sonic artefacts, sound unnatural, and restrict the ability for a user…

In many real-world datasets, like WebVision, the performance of DNN based classifier is often limited by the noisy labeled data. To tackle this problem, some image related side information, such as captions and tags, often reveal underlying…

Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of the training loss. Previous works indicate that the noise is…

Weakly-supervised learning has emerged as a promising approach to leverage limited labeled data in various domains by bridging the gap between fully supervised methods and unsupervised techniques. Acquisition of strong annotations for…

In this report, we present our solution for the task of temporal action localization (detection) (task 1) in ActivityNet Challenge 2020. The purpose of this task is to temporally localize intervals where actions of interest occur and…

This paper proposes to perform unsupervised detection of bioacoustic events by pooling the magnitudes of spectrogram frames after per-channel energy normalization (PCEN). Although PCEN was originally developed for speech recognition, it…

Accurate recognition of Emergency Vehicle (EV) sirens is critical for the integration of intelligent transportation systems, smart city monitoring systems, and autonomous driving technologies. Modern automatic solutions are limited by the…

Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…

Many recently developed object detectors focused on coarse-to-fine framework which contains several stages that classify and regress proposals from coarse-grain to fine-grain, and obtains more accurate detection gradually. Multi-resolution…

This work focuses on online dereverberation for hearing devices using the weighted prediction error (WPE) algorithm. WPE filtering requires an estimate of the target speech power spectral density (PSD). Recently deep neural networks (DNNs)…

In the field of wildlife observation and conservation, approaches involving machine learning on audio recordings are becoming increasingly popular. Unfortunately, available datasets from this field of research are often not optimal learning…

Packet loss is a common and unavoidable problem in voice over internet phone (VoIP) systems. To deal with the problem, we propose a band-split packet loss concealment network (BS-PLCNet). Specifically, we split the full-band signal into…

Direct Preference Optimization (DPO) has emerged as a more computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) with Proximal Policy Optimization (PPO), eliminating the need for reward models and online…

The learning of the region proposal in object detection using the deep neural networks (DNN) is divided into two tasks: binary classification and bounding box regression task. However, traditional RPN (Region Proposal Network) defines these…

Modern neural network architectures have achieved remarkable accuracies but remain highly dependent on their training data, often lacking interpretability in their learned mappings. While effective on large datasets, they tend to overfit on…

Fault detection in electric motors is a critical challenge in various industries, where failures can result in significant operational disruptions. This study investigates the use of Recurrent Neural Networks (RNNs) and Bayesian Neural…

Accurate lesion segmentation in ultrasound images is essential for preventive screening and clinical diagnosis, yet remains challenging due to low contrast, blurry boundaries, and significant scale variations. Although existing deep…

Although the Prototypical Network (ProtoNet) has demonstrated effectiveness in few-shot biological event detection, two persistent issues remain. Firstly, there is difficulty in constructing a representative negative prototype due to the…