@inproceedings{okur-etal-2020-audio,
title = "Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents",
author = "Okur, Eda and
H Kumar, Shachi and
Sahay, Saurav and
Nachman, Lama",
editor = "Zadeh, Amir and
Morency, Louis-Philippe and
Liang, Paul Pu and
Poria, Soujanya",
booktitle = "Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)",
month = jul,
year = "2020",
address = "Seattle, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.challengehml-1.7/",
doi = "10.18653/v1/2020.challengehml-1.7",
pages = "55--59",
abstract = "Building multimodal dialogue understanding capabilities situated in the in-cabin context is crucial to enhance passenger comfort in autonomous vehicle (AV) interaction systems. To this end, understanding passenger intents from spoken interactions and vehicle vision systems is an important building block for developing contextual and visually grounded conversational agents for AV. Towards this goal, we explore AMIE (Automated-vehicle Multimodal In-cabin Experience), the in-cabin agent responsible for handling multimodal passenger-vehicle interactions. In this work, we discuss the benefits of multimodal understanding of in-cabin utterances by incorporating verbal/language input together with the non-verbal/acoustic and visual input from inside and outside the vehicle. Our experimental results outperformed text-only baselines as we achieved improved performances for intent detection with multimodal approach."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="okur-etal-2020-audio">
<titleInfo>
<title>Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eda</namePart>
<namePart type="family">Okur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shachi</namePart>
<namePart type="family">H Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saurav</namePart>
<namePart type="family">Sahay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lama</namePart>
<namePart type="family">Nachman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="given">Pu</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building multimodal dialogue understanding capabilities situated in the in-cabin context is crucial to enhance passenger comfort in autonomous vehicle (AV) interaction systems. To this end, understanding passenger intents from spoken interactions and vehicle vision systems is an important building block for developing contextual and visually grounded conversational agents for AV. Towards this goal, we explore AMIE (Automated-vehicle Multimodal In-cabin Experience), the in-cabin agent responsible for handling multimodal passenger-vehicle interactions. In this work, we discuss the benefits of multimodal understanding of in-cabin utterances by incorporating verbal/language input together with the non-verbal/acoustic and visual input from inside and outside the vehicle. Our experimental results outperformed text-only baselines as we achieved improved performances for intent detection with multimodal approach.</abstract>
<identifier type="citekey">okur-etal-2020-audio</identifier>
<identifier type="doi">10.18653/v1/2020.challengehml-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.challengehml-1.7/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>55</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents
%A Okur, Eda
%A H Kumar, Shachi
%A Sahay, Saurav
%A Nachman, Lama
%Y Zadeh, Amir
%Y Morency, Louis-Philippe
%Y Liang, Paul Pu
%Y Poria, Soujanya
%S Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, USA
%F okur-etal-2020-audio
%X Building multimodal dialogue understanding capabilities situated in the in-cabin context is crucial to enhance passenger comfort in autonomous vehicle (AV) interaction systems. To this end, understanding passenger intents from spoken interactions and vehicle vision systems is an important building block for developing contextual and visually grounded conversational agents for AV. Towards this goal, we explore AMIE (Automated-vehicle Multimodal In-cabin Experience), the in-cabin agent responsible for handling multimodal passenger-vehicle interactions. In this work, we discuss the benefits of multimodal understanding of in-cabin utterances by incorporating verbal/language input together with the non-verbal/acoustic and visual input from inside and outside the vehicle. Our experimental results outperformed text-only baselines as we achieved improved performances for intent detection with multimodal approach.
%R 10.18653/v1/2020.challengehml-1.7
%U https://aclanthology.org/2020.challengehml-1.7/
%U https://doi.org/10.18653/v1/2020.challengehml-1.7
%P 55-59
Markdown (Informal)
[Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents](https://aclanthology.org/2020.challengehml-1.7/) (Okur et al., Challenge-HML 2020)
ACL