中文标题#
HiFi-Stream：使用生成对抗网络的流式语音增强
英文标题#
HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks
中文摘要#
语音增强技术已成为移动设备和语音软件中的核心技术。 尽管如此，现代深度学习解决方案通常需要大量的计算资源，这使得它们在低资源设备上的使用具有挑战性。 我们提出了 HiFi-Stream，这是最近发布的 HiFi++ 模型的优化版本。 我们的实验表明，尽管其大小和计算复杂度相比原始 HiFi++ 有所改进，HiFi-Stream 保留了原始模型的大部分质量，使其成为目前最小和最快的模型之一。 该模型在流式设置中进行了评估，与现代基线方法相比，表现出优越的性能。
英文摘要#
Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices challenging. We present HiFi-Stream, an optimized version of recently published HiFi++ model. Our experiments demonstrate that HiFi-Stream saves most of the qualities of the original model despite its size and computational complexity improved in comparison to the original HiFi++ making it one of the smallest and fastest models available. The model is evaluated in streaming setting where it demonstrates its superior performance in comparison to modern baselines.
PDF 获取#
抖音扫码查看更多精彩内容