3 papers
cs.LG2026
On Optimizing Multimodal Jailbreaks for Spoken Language Models
Aravind Krishnan, Karolina StaÅczak, Dietrich Klakow
As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. S…
cs.CL2024
Joint vs Sequential Speaker-Role Detection and Automatic Speech Recognition for Air-traffic Control
Alexander Blatt, Aravind Krishnan, Dietrich Klakow
Utilizing air-traffic control (ATC) data for downstream natural-language processing tasks requires preprocessing steps. Key steps are the transcription of the data via automatic sp…
cs.CL2024
On the Encoding of Gender in Transformer-based ASR Representations
Aravind Krishnan, Badr M. Abdullah, Dietrich Klakow
While existing literature relies on performance differences to uncover gender biases in ASR models, a deeper analysis is essential to understand how gender is encoded and utilized…