Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents

Eda Okur, Shachi H Kumar, Saurav Sahay, Lama Nachman


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.
Anthology ID:
2020.challengehml-1.7
Volume:
Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML)
Month:
July
Year:
2020
Address:
Seattle, USA
Venues:
ACL | Challenge-HML | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
55–59
Language:
URL:
https://aclanthology.org/2020.challengehml-1.7
DOI:
10.18653/v1/2020.challengehml-1.7
Bibkey:
Cite (ACL):
Eda Okur, Shachi H Kumar, Saurav Sahay, and Lama Nachman. 2020. Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents. In Second Grand-Challenge and Workshop on Multimodal Language (Challenge-HML), pages 55–59, Seattle, USA. Association for Computational Linguistics.
Cite (Informal):
Audio-Visual Understanding of Passenger Intents for In-Cabin Conversational Agents (Okur et al., Challenge-HML 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.challengehml-1.7.pdf
Video:
 http://slideslive.com/38931265
Video:
 http://slideslive.com/38931265