FastEnhancer通过简化结构实现低延迟语音增强，适合实时场景。
FastEnhancer: Speed-Optimized Streaming Neural Speech Enhancement
- 采用轻量级编码器-解码器结构与高效RNNFormer模块
- 在单核CPU上达到最快处理速度，同时保持顶尖音质与可懂度
- 专为低延迟设计，适合会议、助听器等实时应用
流式语音增强是在线会议、智能家居和助听器等实时应用的关键任务。基于深度神经网络的方法虽性能出色，但计算开销大。尽管近期模型已减少参数量和乘加操作，其复杂架构仍会在普通硬件上引入显著处理延迟。本文提出FastEnhancer，一种专为最小化实际延迟设计的流式神经语音增强模型，采用简洁的编码器-解码器结构与高效的RNNFormer块。在多种客观指标评估中，FastEnhancer在保持领先语音质量与可懂度的同时，在单个CPU线程上实现了最快的处理速度。代码与预训练权重已公开（https://github.com/aask1357/fastenhancer）。
原文摘要 · Abstract (English)
Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial computational resources. Although recent neural speech enhancement models have succeeded in reducing the number of parameters and multiply-accumulate operations, their sophisticated architectures often introduce significant processing latency on common hardware. In this work, we propose FastEnhancer, a streaming neural speech enhancement model designed explicitly to minimize real-world latency. It features a simple encoder-decoder structure with efficient RNNFormer blocks. Evaluations on various objective metrics show that FastEnhancer achieves state-of-the-art speech quality and intelligibility while simultaneously demonstrating the fastest processing speed on a single CPU thread. Code and pre-trained weights are publicly available (https://github.com/aask1357/fastenhancer).
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。