DOA derives a proxy alignment from decoder self-attention to support training-free long-form simultaneous speech-to-text translation with off-the-shelf SpeechLLMs.
Siqi Ouyang, Xi Xu, and Lei Li
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
DOA derives a proxy alignment from decoder self-attention to support training-free long-form simultaneous speech-to-text translation with off-the-shelf SpeechLLMs.