Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation
원문 초록
Recent advancement of large language models (LLMs) has led to significant breakthroughs across various tasks, laying the foundation for the development of LLM-based speech translation systems. Existing methods primarily focus on aligning inputs and outputs across modalities while overlooking deeper semantic alignment within model representations. To address this limitation, we propose an Adaptive Inner Speech-Text Alignment (AI-STA) method to bridge the modality gap by explicitly aligning speech and text representations at selected layers within LLMs. To achieve this, we leverage the optimal transport (OT) theory to quantify fine-grained representation discrepancies between speech and text. Furthermore, we utilize the cross-modal retrieval technique to identify the layers that are best suited for alignment and perform joint training on these layers. Experimental results on speech translation (ST) tasks demonstrate that AI-STA significantly improves the translation performance of large speech-text models (LSMs), outperforming previous state-of-the-art approaches. Our findings highlight the importance of inner-layer speech-text alignment in LLMs and provide new insights into enhancing cross-modal learning.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025
Gender Bias in English-to-Greek Machine Translation
Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
TACTIC: Translation Agents with Cognitive-Theoretic Interactive Collaboration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.