发表机构
Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出进度感知投机草稿模型，通过循环传播声学进度状态指导令牌生成，在五个ASR测试集上实现无损加速，优于基线。
AI 中文摘要
投机解码可加速自回归自动语音识别（ASR），但对齐感知草稿模型的接受长度会随着草稿视界增加而饱和。我们提出一种进度感知的投机草稿模型，该模型在草稿步骤间循环传播声学进度状态，并将其反馈到音频交叉注意力中以指导令牌生成。我们在可变草稿视界上联合训练草稿模型和进度预测器。在五个ASR测试集上，我们的方法相对于仅目标自回归解码，在Qwen3-ASR-0.6B和Qwen3-ASR-1.7B上分别实现了无损的宏平均端到端加速1.657倍和1.227倍。与AnchorDraft相比，我们的方法将宏平均加速分别提高了34.3%和9.0%。视界扫描显示，接受长度在基线饱和点之后持续增长。代码可在该HTTPS URL获取。
英文摘要
Speculative decoding accelerates autoregressive automatic speech recognition (ASR), but the acceptance length of alignment-aware drafters can saturate as the draft horizon increases. We propose a progress-aware speculative drafter that recurrently propagates an acoustic progress state across draft steps and feeds it back into audio cross-attention to guide token generation. We jointly train the drafter and progress predictor over variable draft horizons. On five ASR test sets, our method achieves lossless, macro-averaged end-to-end speedups of 1.657x and 1.227x over target-only autoregressive decoding with Qwen3-ASR-0.6B and Qwen3-ASR-1.7B, respectively. Relative to AnchorDraft, our method improves the macro-averaged speedup by 34.3% and 9.0%, respectively. Horizon sweeps show continued growth in acceptance length beyond the baselines' saturation. Code is available at https://github.com/yuanyuanjia71-spec/ProgDraft.
Comments5 pages, 2 figures, 2 tables
