AIConfPaper
← Search

Simran Naagar

2 accepted papers

2025

Bridging Modality Gap with Large Speech and Language Models for End-to-End Speech-to-Text Translation

Weitai Zhang, Simran Naagar, Zhongyi Ye, Peiwang Tang, Xinyuan Zhou, Junhua Liu +1
ICASSP 2025accepted

End-to-end speech-to-text translation (E2E ST) has increasingly aroused interest and attention recently, attempting to address the problem of data scarcity and modeling burden. Several attempts exploring the combination of Large Speech and Language Models into a unified model to improve E2E ST are c…

Cited by 0Source ↗Scholar ↗
2025

Semi-Supervised Multilingual Alignment with Lexical Memory for Massively Parallel Text Mining

Weitai Zhang, Peiwang Tang, Chao Lin, Simran Naagar, Zhongyi Ye, Junhua Liu
ICASSP 2025accepted

Existing state-of-the-art techniques that employ multilingual sentence embeddings for mining parallel texts predominantly rely on extensive supervision, which often results in sub-optimal performance in the absence of large-scale parallel training datasets. In this study, we introduce a novel method…

Cited by 0Source ↗Scholar ↗