HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks
This work addresses computational efficiency for speech enhancement on mobile and voice software, but it is incremental as it builds on an existing model.
The authors tackled the problem of deploying speech enhancement on low-resource devices by optimizing the HiFi++ model, resulting in HiFi-Stream, which maintains most of the original quality while being one of the smallest and fastest models available.
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.