Large pre-trained speech models are widely used as the de-facto paradigm...
Large Language Models (LLMs) have been applied in the speech domain, oft...
We introduce the Universal Speech Model (USM), a single large model that...
We propose AnyTOD, an end-to-end task-oriented dialog (TOD) system with
...
Most research on task oriented dialog modeling is based on written text
...
Knowledge (including structured knowledge such as schema and ontology, a...
Carefully-designed schemas describing how to collect and annotate dialog...
In this paper, we describe novel components for extracting clinically
re...
There is a growing interest in creating tools to assist in clinical note...
Speech applications dealing with conversations require not only recogniz...
We present results that show it is possible to build a competitive, grea...
Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Ne...