Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …

Recent advancements in deep learning (DL) have posed a significant challenge for
automatic speech recognition (ASR). ASR relies on extensive training datasets, including …

Federated learning (FL) is an approach within the realm of machine learning (ML) that
allows the use of distributed data without compromising personal privacy. In FL, it becomes …

The growth in online child exploitation material is a significant challenge for European Law
Enforcement Agencies (LEAs). One of the most important sources of such online information …

Federated learning (FL) has gained substantial attention in recent years due to data privacy
concerns related to the pervasiveness of consumer devices that continuously collect data …

Decentralized optimization with multiple networked clients/learners has advanced machine
learning significantly over the past few years. When data distributions at different …

Training Automatic Speech Recognition (ASR) models under federated learning (FL)
settings has attracted a lot of attention recently. However, the FL scenarios often presented …

This paper investigates methods to effectively retrieve speaker information from the
personalized speaker adapted neural network acoustic models (AMs) in automatic speech …

With the growing availability of smart devices and cloud services, personal speech
assistance systems are increasingly used on a daily basis. Most devices redirect the voice …

Cross-device federated learning (FL) protects user privacy by collaboratively training a
model on user devices, therefore eliminating the need for collecting, storing, and manually …