3 citations · 3 across the 5 of their papers we have counts for
5 papers
CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment
Anurag Kumar, Raghuveer Peri, Jon Burnsky +4
Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a highe…
SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models
Anurag Kumar, Rohit Paturi, Amber Afshan +1
Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often…
Using RLHF to align speech enhancement approaches to mean-opinion quality scores
Anurag Kumar, Andrew Perrault, Donald S. Williamson
Objective speech quality measures are typically used to assess speech enhancement algorithms, but it has been shown that they are sub-optimal as learning objectives because they do…
Curriculum optimization for low-resource speech recognition
Anastasia Kuznetsova, Anurag Kumar, Jennifer Drexler Fox +1
Modern end-to-end speech recognition models show astonishing results in transcribing audio signals into written text. However, conventional data feeding pipelines may be sub-optima…
A bandit approach to curriculum generation for automatic speech recognition
Anastasia Kuznetsova, Anurag Kumar, Francis M. Tyers
The Automated Speech Recognition (ASR) task has been a challenging domain especially for low data scenarios with few audio examples. This is the main problem in training ASR system…