发表机构
MAUM AI Inc.（MAUM AI 公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究探索利用预训练ASR模型，通过SliceGPT剪枝提取紧凑编码器，实现无需微调的唤醒词检测，实验显示通道缩减50%时性能稳定。
AI 中文摘要
近年来，ASR的发展日益强调跨不同领域和声学条件的泛化能力。现有方法通常通过额外训练或任务特定模块，将预训练的ASR模型适配到唤醒词（WuW）检测等前端功能上。在本工作中，我们探索了在不进行基于梯度的微调的情况下，使用共享的预训练ASR骨干网络进行唤醒词检测，并考察是否可以利用基于PCA的SliceGPT结构化剪枝方法提取出紧凑的编码器。使用Parakeet-TDT-0.6B-v3和Moonshine-base进行的实验表明，当编码器通道维度缩减50%时，唤醒词检测性能保持相对稳定。这些结果表明，无需微调即可从预训练ASR模型中派生出任务相关的紧凑编码器。
英文摘要
Recent ASR development has placed growing emphasis on generalization across diverse domains and acoustic conditions. Existing approaches typically adapt pretrained ASR models to front-end functions such as wake-up word (WuW) detection through additional training or task-specific modules. In this work, we explore the use of a shared pretrained ASR backbone for WuW detection without gradient-based fine-tuning and examine whether a compact encoder can be extracted using the PCA-based structured pruning approach of SliceGPT. Experiments with Parakeet-TDT-0.6B-v3 and Moonshine-base show that WuW detection performance remains relatively stable when the encoder channel dimension is reduced by 50%. These results suggest that task-relevant compact encoders can be derived from pretrained ASR models without fine-tuning.
CommentsSubmitted to IEEE ICASSP 2027
