#9012. Admitting the addressee detection faultiness of voice assistants to improve the activation performance using a continuous learning framework

August 2026publication date
Proposal available till 29-05-2025
4 total number of authors per manuscript3510 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Experimental and Cognitive Psychology;
Software;
Cognitive Neuroscience;
Artificial Intelligence;
Places in the authors’ list:
place 1place 2place 3place 4
FreeFreeFreeFree
1050 $940 $820 $700 $
Contract №9012.1 Contract №9012.2 Contract №9012.3 Contract №9012.4
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)

Abstract:
Voice assistants need predetermined activation actions to start a conversation. Unfortunately, these systems can also confuse when the wake-word, or a phonetically similar phrase, has been said but no interaction with the system is intended by the user. This study reviews the existing solutions embedded into the voice assistant apps to allow better addressee detection and activation performance of the app. We discuss both the loopholes a user can find in the settings menu, such as the keyword change function, and the smart strategies based on machine learning.
Keywords:
Addressee detection; Continuous learning; Identical HCI-HHI

Contacts :
0