Search Results for author:
Found 4 papers, 0 papers with code
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
Despite safety guardrails, experiments on jailbreaking demonstrate the vulnerability of SLMs to adversarial perturbations and transfer attacks, with average attack success rates of 90% and 10% respectively when evaluated on a dataset of carefully designed harmful questions spanning 12 different toxic categories.
Knowledge Transfer for Efficient On-device False Trigger Mitigation
But in case of a false trigger, transcribing the audio using ASR itself is strongly undesirable.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Complementary Language Model and Parallel Bi-LRNN for False Trigger Mitigation
In this paper, we propose a novel solution to the FTM problem by introducing a parallel ASR decoding process with a special language model trained from "out-of-domain" data sources.
Lattice-based Improvements for Voice Triggering Using Graph Neural Networks
A pure trigger-phrase detector model doesn't fully utilize the intent of the user speech whereas by using the complete decoding lattice of user audio, we can effectively mitigate speech not intended for the smart assistant.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
