3 papers
cs.IR2026
Visual RAG Toolkit: Scaling Multi-Vector Visual Retrieval with Training-Free Pooling and Multi-Stage Search
Ara Yeroyan
Multi-vector visual retrievers (e.g., ColPali-style late interaction models) deliver strong accuracy, but scale poorly because each page yields thousands of vectors, making indexin…
cs.SD2025
Methods to Increase the Amount of Data for Speech Recognition for Low Resource Languages
Alexan Ayrapetyan, Sofia Kostandian, Ara Yeroyan +5
This study explores methods to increase data volume for low-resource languages using techniques such as crowdsourcing, pseudo-labeling, advanced data preprocessing and various perm…
cs.CL2024
Enabling ASR for Low-Resource Languages: A Comprehensive Dataset Creation Approach
Ara Yeroyan, Nikolay Karpov
In recent years, automatic speech recognition (ASR) systems have significantly improved, especially in languages with a vast amount of transcribed speech data. However, ASR systems…