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...
Language models are increasingly being deployed for general problem solv...
Data multiplexing is a recently proposed method for improving a model's
...
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...
While large language models (LLMs) have demonstrated impressive capabili...
Carefully-designed schemas describing how to collect and annotate dialog...
Task-oriented dialogue (TOD) systems are required to identify key inform...
We propose a novel framework for modeling the interaction between graphi...
In this paper, we describe novel components for extracting clinically
re...
This report describes the aggregation and anonymization process applied ...
There is a growing interest in creating tools to assist in clinical note...
Recently we proposed the Span Attribute Tagging (SAT) Model (Du et al., ...
Speech applications dealing with conversations require not only recogniz...
Unitary Evolution Recurrent Neural Networks (uRNNs) have three attractiv...
This paper describes novel models tailored for a new application, that o...
Named Entity Recognition (NER) has been mostly studied in the context of...
In this paper, we generalize image (texture) statistical descriptors and...