发表机构
Carrot, Inc（胡萝卜公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究用于流式关键词识别的累积和可组合相位传输，通过将声学帧投影到复数通道，经酉旋转传输等操作，在Google Speech Commands v2数据集上取得有竞争力准确率，且训练速度快、延迟低，是简单低成本时间原语。
AI 中文摘要
状态空间序列模型因能保持紧凑循环状态而对流式语音有吸引力，但扫描式训练内核在短音频任务中常数不利。本文研究累积和可组合相位传输，这是一种用于关键词识别的流式原生时间层。各层将声学帧投影到复数通道，通过学习的酉旋转进行传输，利用前缀差累积有限窗口，并应用门控残差更新。酉传输是关键约束，逆旋转范数为1，能保持前缀项良好条件。在Google Speech Commands v2数据集上，mel + 累积和模型与紧凑基线相比保持了有竞争力的准确率。最强单种子运行达到97.3%的测试准确率，不同参数的模型也有不错表现。在累积和与扫描的基准测试中，累积和 + 窗口给出了可比的准确率，同时训练速度快1.07倍，单例延迟从7.09毫秒降至5.01毫秒。这些结果支持累积和相位传输作为流式关键词识别的简单低成本时间原语。
英文摘要
State-space sequence models are attractive for streaming speech because they maintain compact recurrent state, but scan-style training kernels can have unfavorable constants for short audio tasks. We study cumsum-composable phase transport, a streaming-native temporal layer for keyword spotting. Each layer projects acoustic frames to complex channels, transports them by learned unitary rotations, accumulates a finite window using prefix differences, and applies a gated residual update. The same prefix representation gives exact batched training with ordinary cumulative sums and exact online inference with one prefix update per frame. Unitary transport is the key constraint: inverse rotations have norm one, keeping prefix terms well conditioned while memory is supplied by windows or block readouts. On Google Speech Commands v2 with 12 labels, mel+cumsum models retain competitive accuracy with compact baselines. The strongest single-seed run reaches 97.3\% test accuracy; a 51.6K-parameter tied model also reaches 97.3\%, and a 24.8K tied model reaches 96.8\% versus 97.1\% for a 25.6K MelCNNMaxPool baseline. In a matched cumsum-versus-scan benchmark, cumsum+window gives comparable accuracy, 94.82\% versus 94.33\%, while training 1.07x faster and reducing single-example latency from 7.09 ms to 5.01 ms on a Tesla T4. These results support cumsum phase transport as a simple low-cost temporal primitive for streaming keyword spotting.
