HiFi-Stream:基于生成对抗网络的流式语音增强
HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks
AI总结:
本文提出低计算量流式语音增强模型 HiFi-Stream,在保留 Hi++ 主要音质的同时显著减小尺寸和复杂度,并在流式评测中优于现代基线。
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。然而,现代深度学习解决方案通常需要大量计算资源,这使其在低资源设备上的应用颇具挑战。我们提出 HiFi-Stream,即近期发布的 HiFi++ 模型的优化版本。实验表明,尽管 HiFi-Stream 相比原始 HiFi++ 在模型尺寸和计算复杂度方面均有所改善,它仍保留了原模型的大部分质量,使其成为目前可用的最小、最快模型之一。该模型在流式设置下进行评估,并在与现代基线模型的比较中展现出优越性能。
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。