Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

The emerging field of artificial intelligence of things (AIoT, AI+ IoT) is driven by the
widespread use of intelligent infrastructures and the impressive success of deep learning …

Large language models have recently achieved state of the art performance across a wide
variety of natural language tasks. Meanwhile, the size of these models and their latency …

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the
device to preserve only the speech signals from a target user, as part of a streaming speech …

Self-supervised speech representation learning (speech SSL) has demonstrated the benefit
of scale in learning rich representations for Automatic Speech Recognition (ASR) with …

The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse
subnetworks (ie, winning tickets) that can be trained in isolation to match full accuracy …

Large language models have become increasingly difficult to train because of the growing
computation time and cost. In this work, we present SRU++, a highly-efficient architecture …

There is a growing interest in the speech community in developing Recurrent Neural
Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications …

ABSTRACT Automatic Speech Recognition (ASR) is an active field of research due to its
large number of applications and the proliferation of interfaces or computing devices that …

Implementing edge artificial intelligence (AI) inference and training is challenging with
current memory technologies. As deep neural networks (DNNs) grow in size, this problem is …