← Search

Mingjia Yu

2 accepted papers

2025

Adversarial Speech-Text Pre-Training for Speech Translation

ICASSP 2025accepted

Large-scale pre-training has been shown to benefit speech translation tasks. However, existing multimodal pre-training efforts rely on parallel corpora for semantic alignment, potentially limiting performance to the scale of available data and causing data imbalance. Hence, we propose an adversarial…

Cited by 0SourceScholar
2025

Large Language Models Are Efficient Learners as Zero-Shot Speech Translators

ICASSP 2025accepted

Significant progress has recently been made in combining Speech Foundation Models (SFMs) and Large Language Models (LLMs) into a unified model to tackle Speech-to-Text Translation (ST) tasks. However, fine-tuning LLMs to adapt to specific downstream tasks requires substantial resources, which is oft…

Cited by 0SourceScholar