SimulU: Training-free Policy for Long-form Simultaneous Speech-to-Speech Translation
This addresses the need for efficient real-time multilingual communication in meeting and streaming platforms, offering a training-free solution for long-form scenarios.
The paper tackled the problem of simultaneous speech-to-speech translation for long-form, continuous speech by proposing SimulU, a training-free policy that uses history management and speech output selection strategies. It achieved a better or comparable quality-latency trade-off against strong cascaded models on MuST-C across 8 languages.
Simultaneous speech-to-speech translation (SimulS2S) is essential for real-time multilingual communication, with increasing integration into meeting and streaming platforms. Despite this, SimulS2S remains underexplored in research, where current solutions often rely on resource-intensive training procedures and operate on short-form, pre-segmented utterances, failing to generalize to continuous speech. To bridge this gap, we propose SimulU, the first training-free policy for long-form SimulS2S. SimulU adopts history management and speech output selection strategies that exploit cross-attention in pre-trained end-to-end models to regulate both input history and output generation. Evaluations on MuST-C across 8 languages show that SimulU achieves a better or comparable quality-latency trade-off against strong cascaded models. By eliminating the need for ad-hoc training, SimulU offers a promising path to end-to-end SimulS2S in realistic, long-form scenarios.