8 papers
InterCorrect: Intersection-Aware Correction of Demographic Model Merging for Fair ASR
Ashley E. Bravo-Bravo, Yuchen Zhang, Haralambos Mouratidis +2
Automatic Speech Recognition (ASR) systems often show uneven performance across demographic groups, and errors can be especially difficult to address for speakers belonging to mult…
Pruning for Efficiency, Paying in Fairness: Demographic Disparities in Pruned Speech-LLMs
Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar
Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggregate word error rate (WER), whi…
CLARA: Clip-Level Multimodal Alignment with VLM-Derived Rationales for Hateful Video Detection
Yuchen Zhang, Shuang Dai, Zeyu Fu +3
Hateful video detection has become increasingly important with the rapid growth of video-centric social media platforms, given the serious risks that hate speech poses to both indi…
CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning
Ganesh Pavan Kartikeya Bharadwaj Kolluri, Yuchen Zhang, Michael Kampouridis +1
Modern automated audio captioning systems pair a frozen audio encoder with a large language model (LLM) via a trainable projector, incurring the encoder's inference cost and bottle…
On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR
Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar
Automatic speech recognition (ASR) has advanced rapidly in recent years, driven by large-scale pretrained models and end-to-end architectures such as SLAM-ASR. A key component of S…
OasisSimp: An Open-source Asian-English Sentence Simplification Dataset
Hannah Liu, Muxin Tian, Iqra Ali +8
Sentence simplification aims to make complex text more accessible by reducing linguistic complexity while preserving the original meaning. However, progress in this area remains li…
Speak in Context: Multilingual ASR with Speech Context Alignment via Contrastive Learning
Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar
Automatic speech recognition (ASR) has benefited from advances in pretrained speech and language models, yet most systems remain constrained to monolingual settings and short, isol…
SiTSE: Sinhala Text Simplification Dataset and Evaluation
Surangika Ranathunga, Rumesh Sirithunga, Himashi Rathnayake +4
Text Simplification is a task that has been minimally explored for low-resource languages. Consequently, there are only a few manually curated datasets. In this paper, we present a…