用状态空间模型Mamba实现高效精准的语音关键词识别
Keyword Mamba: Spoken Keyword Spotting with State Space Models
- 采用Mamba模型沿时间轴建模，替代传统注意力机制
- 在谷歌语音命令数据集上参数更少、计算成本更低、准确率高
- 首次将状态空间模型用于关键词检测，适合资源受限场景
关键词识别（KWS）是语音处理中的核心任务，广泛应用于语音助手和智能设备。尽管卷积神经网络（CNN）、循环神经网络（RNN）和变压器（Transformer）等深度学习模型表现良好，但通常难以同时处理长时依赖且保持高效。本文提出Keyword Mamba，一种基于状态空间模型（SSM）Mamba的新架构。该模型沿时间轴应用Mamba，并探索其替代Transformer中自注意力模块的可行性。我们在Google Speech Commands数据集上进行了测试，结果表明，Keyword Mamba在参数更少、计算开销更低的情况下仍达到优异的识别准确率。据我们所知，这是首个将状态空间模型用于KWS的工作，表明Mamba在语音任务中具有巨大潜力。
原文摘要 · Abstract (English)
Keyword spotting (KWS) is an essential task in speech processing. It is widely used in voice assistants and smart devices. Deep learning models like CNNs, RNNs, and Transformers have performed well in KWS. However, they often struggle to handle long-term patterns and stay efficient at the same time. In this work, we present Keyword Mamba, a new architecture for KWS. It uses a neural state space model (SSM) called Mamba. We apply Mamba along the time axis and also explore how it can replace the self-attention part in Transformer models. We test our model on the Google Speech Commands datasets. The results show that Keyword Mamba reaches strong accuracy with fewer parameters and lower computational cost. To our knowledge, this is the first time a state space model has been used for KWS. These results suggest that Mamba has strong potential in speech-related tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。