Search Results for author:
Found 7 papers, 2 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.
VoxWatch: An open-set speaker recognition benchmark on VoxCeleb
Prior studies on this problem are sparse, and lack a common benchmark for systematic evaluations.
VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge
This paper summarises the findings from the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22), which was held in conjunction with INTERSPEECH 2022.
Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech
Also, most of these models are trained with synthetic mixtures and do not generalize to real conversational data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors
We have recently introduced a fast scoring algorithm for a discriminatively trained HT-PLDA backend.
Generative Modelling for Unsupervised Score Calibration
Score calibration enables automatic speaker recognizers to make cost-effective accept / reject decisions.
