Alexander W. Churchill — accepted AI-conference papers

2025

SELMA: A Speech-Enabled Language Model for Virtual Assistant Interactions

Dominik Wagner, Alexander W. Churchill, Siddharth Sigtia, Erik Marchi

ICASSP 2025accepted

In this work, we present and evaluate SELMA, a Speech-Enabled Language Model for virtual Assistant interactions that integrates audio and text as inputs to a Large Language Model (LLM). SELMA is designed to handle three primary and two auxiliary tasks related to interactions with virtual assistants…

Cited by 0 Source ↗Scholar ↗

2024

A Multimodal Approach to Device-Directed Speech Detection with Large Language Models

Dominik Wagner, Alexander W. Churchill, Siddharth Sigtia, Panayiotis G. Georgiou, Matt Mirsamadi, Aarshee Mishra +1

ICASSP 2024accepted

Interactions with virtual assistants typically start with a predefined trigger phrase followed by the user command. To make interactions with the assistant more intuitive, we explore whether it is feasible to drop the requirement that users must begin each command with a trigger phrase. We explore t…

Cited by 0 Source ↗Scholar ↗