发表机构
Hanyang University（汉阳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究在CPU上运行流式语音增强器的成本，将FastEnhancer-Medium移植到faster-enhancer.c，通过专门化运行时各层等方法加速，在多设备上有良好表现，还探讨了速度与部署成本关系，运行时作为无依赖库发布。
AI 中文摘要
这是一项关于在CPU上运行流式语音增强器成本的实现与测量研究。我们将48kHz的FastEnhancer-Medium移植到faster-enhancer.c，这是一个在初始化时选择六个int8 GEMM层的C运行时，架构和权重不变。在同一台机器上，一个苹果M2核心的实时因子达到0.069，而fp32 ONNX运行时图为0.230，加速了3.3倍。三星Galaxy S23+（骁龙8 Gen 2）达到0.096。加速来自于围绕一个固定模型对运行时的每一层进行专门化。每帧重新计算激活范围，无需校准集；k=3卷积使用Winograd F(2,3)；跨阶段状态为fp16；GRU和反量化尾声融合；启动后不进行分配。在超过824个VoiceBank-DEMAND话语上，该引擎将fp32跟踪到PESQ在-0.006以内，SNR在-0.08dB以内。仅速度不能决定部署成本。只要麦克风打开，增强器就占用一小部分核心，因此其实时因子是一个占空比。基准测试快速处理文件；音频回调则不然。以6.67ms的截止时间进行调度，每帧成本为4.2倍，节省49%的能量，最便宜的核心放置会错过96%的截止时间。一个架构家族内的所有SIMD层输出字节相同。该运行时作为一个无依赖库发布。
英文摘要
This is an implementation and measurement study of what it costs to run a streaming speech enhancer on a CPU. We port FastEnhancer-Medium at 48 kHz to faster-enhancer.c, a C runtime with six int8 GEMM tiers selected at initialization, leaving architecture and weights untouched. One Apple M2 core reaches 0.069 real-time factor, against 0.230 for the fp32 ONNX Runtime graph on the same machine, a 3.3x speedup. A Galaxy S23+ (Snapdragon 8 Gen 2) reaches 0.096. The speedup comes from specializing every layer of the runtime around one fixed model. Activation ranges are recomputed per frame, so no calibration set is needed; the k=3 convolutions use Winograd F(2,3); cross-stage state is fp16; the GRU and the dequantization epilogues are fused; and nothing is allocated after startup. Over 824 VoiceBank-DEMAND utterances the engine tracks fp32 to within -0.006 PESQ and -0.08 dB SNR. Speed alone does not settle deployment cost. The enhancer holds a fraction of a core for as long as the microphone is open, so its real-time factor is a duty cycle. A benchmark races through a file; an audio callback does not. Pacing to the 6.67 ms deadline costs 4.2x per frame, saves 49% of the energy, and leaves the cheapest core placement missing 96% of its deadlines. All SIMD tiers within an architecture family emit byte-identical output. The runtime is released as a dependency-free library.
Comments5 pages, 2 figures, 2 tables. Code: https://github.com/kdrkdrkdr/faster-enhancer.c
