Spoken keyword spotting (KWS) deals with the identification of keywords in audio streams
and has become a fast-growing technology thanks to the paradigm shift introduced by deep …

Describes an audio dataset of spoken words designed to help train and evaluate keyword
spotting systems. Discusses why this task is an interesting challenge, and why it requires a …

Keyword spotting is an important research field because it plays a key role in device wake-
up and user interaction on smart devices. However, it is challenging to minimize errors while …

Keyword spotting (KWS) plays a critical role in enabling speech-based user interactions on
smart devices. Recent developments in the field of deep learning have led to wide adoption …

This paper introduces a convolutional recurrent network with attention for speech command
recognition. Attention models are powerful tools to improve performance on natural …

Real-time multi-task multi-model (MTMM) workloads, a new form of deep learning inference
workloads, are emerging for applications areas like extended reality (XR) to support …

Abstract Knowledge Distillation (KD) aims at transferring the knowledge of a well-performed
neural network (the {\it teacher}) to a weaker one (the {\it student}). A peculiar phenomenon …

Driven by the wide adoption of deep neural networks (DNNs) across different application
domains, multi-tenancy execution, where multiple DNNs are deployed simultaneously on …

Building efficient architecture in neural speech processing is paramount to success in
keyword spotting deployment. However, it is very challenging for lightweight models to …

The brain-inspired spiking neural networks (SNNs) are receiving increasing attention due to
their asynchronous event-driven characteristics and low power consumption. As attention …