@inproceedings{yang-etal-2025-spoken,
title = "Spoken Conversational Agents with Large Language Models",
author = "Yang, Huck and
Stolcke, Andreas and
Heck, Larry P.",
editor = "Pyatkin, Valentina and
Vlachos, Andreas",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-tutorials.3/",
pages = "7--8",
ISBN = "979-8-89176-336-4",
abstract = "Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-grounded systems. We frame adaptation of text LLMs to audio, cross-modal alignment, and joint speech{--}text training; review datasets, metrics, and robustness across accents; and compare design choices (cascaded vs. E2E, post-ASR correction, streaming). We link industrial assistants to current open-domain and task-oriented agents, highlight reproducible baselines, and outline open problems in privacy, safety, and evaluation. Attendees leave with practical recipes and a clear systems-level roadmap."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-spoken">
<titleInfo>
<title>Spoken Conversational Agents with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huck</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Stolcke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larry</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Heck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valentina</namePart>
<namePart type="family">Pyatkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-336-4</identifier>
</relatedItem>
<abstract>Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-grounded systems. We frame adaptation of text LLMs to audio, cross-modal alignment, and joint speech–text training; review datasets, metrics, and robustness across accents; and compare design choices (cascaded vs. E2E, post-ASR correction, streaming). We link industrial assistants to current open-domain and task-oriented agents, highlight reproducible baselines, and outline open problems in privacy, safety, and evaluation. Attendees leave with practical recipes and a clear systems-level roadmap.</abstract>
<identifier type="citekey">yang-etal-2025-spoken</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-tutorials.3/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>7</start>
<end>8</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spoken Conversational Agents with Large Language Models
%A Yang, Huck
%A Stolcke, Andreas
%A Heck, Larry P.
%Y Pyatkin, Valentina
%Y Vlachos, Andreas
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-336-4
%F yang-etal-2025-spoken
%X Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-grounded systems. We frame adaptation of text LLMs to audio, cross-modal alignment, and joint speech–text training; review datasets, metrics, and robustness across accents; and compare design choices (cascaded vs. E2E, post-ASR correction, streaming). We link industrial assistants to current open-domain and task-oriented agents, highlight reproducible baselines, and outline open problems in privacy, safety, and evaluation. Attendees leave with practical recipes and a clear systems-level roadmap.
%U https://aclanthology.org/2025.emnlp-tutorials.3/
%P 7-8
Markdown (Informal)
[Spoken Conversational Agents with Large Language Models](https://aclanthology.org/2025.emnlp-tutorials.3/) (Yang et al., EMNLP 2025)
ACL
- Huck Yang, Andreas Stolcke, and Larry P. Heck. 2025. Spoken Conversational Agents with Large Language Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, pages 7–8, Suzhou, China. Association for Computational Linguistics.