Related papers: Head-Related Transfer Function Individualization U…

Transformer requires a fixed number of layers and heads which makes them inflexible to the complexity of individual samples and expensive in training and inference. To address this, we propose a sample-based Dynamic Hierarchical Transformer…

In this work, we propose a deep beamforming framework for speech enhancement in dynamic acoustic environments. The framework learns time-varying beamformer weights from noisy multichannel signals via a deep neural network, guided by a…

Sound processing in the human auditory system is complex and highly non-linear, whereas hearing aids (HAs) still rely on simplified descriptions of auditory processing or hearing loss to restore hearing. Even though standard HA…

This paper presents a Head-Related Transfer Function (HRTF)-guided framework for binaural Target Speaker Extraction (TSE) from mixtures of concurrent sources. Unlike conventional TSE methods based on Direction of Arrival (DOA) estimation or…

Federated learning allows clients to collaboratively learn statistical models while keeping their data local. Federated learning was originally used to train a unique global model to be served to all clients, but this approach might be…

Deep neural networks have shown the ability to extract universal feature representations from data such as images and text that have been useful for a variety of learning tasks. However, the fruits of representation learning have yet to be…

Human Trajectory Forecasting (HTF) predicts future human movements from past trajectories and environmental context, with applications in Autonomous Driving, Smart Surveillance, and Human-Robot Interaction. While prior work has focused on…

Neural-based multi-task learning (MTL) has gained significant improvement, and it has been successfully applied to recommendation system (RS). Recent deep MTL methods for RS (e.g. MMoE, PLE) focus on designing soft gating-based…

Recent studies show that apparent personality traits can be reflected from human facial behavior dynamics. However, most existing methods can only encode single-scale short-term facial behaviors in the latent features for personality…

Although many deep learning (DL) algorithms have been proposed for the IMU-based HAR domain, traditional machine learning that utilizes handcrafted time series features (TSFs) still often performs well. It is not rare that combinations…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

In response to the challenges posed by non-independent and identically distributed (non-IID) data and the escalating threat of privacy attacks in Federated Learning (FL), we introduce HyperFedNet (HFN), a novel architecture that…

Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications. Existing approaches…

Machine learning methods for estimating heterogeneous treatment effects (HTE) facilitate large-scale personalized decision-making across various domains such as healthcare, policy making, education, and more. Current machine learning…

This paper addresses the problem of binaural localization of a single speech source in noisy and reverberant environments. For a given binaural microphone setup, the binaural response corresponding to the direct-path propagation of a single…

With the increasing implementation of machine learning models on edge or Internet-of-Things (IoT) devices, deploying advanced models on resource-constrained IoT devices remains challenging. Transformer models, a currently dominant neural…

A learning-based method for estimating the magnitude distribution of sound fields from spatially sparse measurements is proposed. Estimating the magnitude distribution of acoustic transfer function (ATF) is useful when phase measurements…

We propose PressureTransferNet, a novel method for Human Activity Recognition (HAR) using ground pressure information. Our approach generates body-specific dynamic ground pressure profiles for specific activities by leveraging existing…

We propose HHFT (Hierarchical Heterogeneous Feature Transformer), a Transformer-based architecture tailored for industrial CTR prediction. HHFT addresses the limitations of DNN through three key designs: (1) Semantic Feature Partitioning:…

Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep…