ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2503.17141
32
0

HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks

21 March 2025
Ekaterina Dmitrieva
Maksim Kaledin
ArXivPDFHTML
Abstract

Speech Enhancement techniques have become core technologies in mobile devices and voice software simplifying downstream speech tasks. Still, modern Deep Learning (DL) 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 HiFiStream saves most of the qualities of the original model despite its size and computational complexity: the lightest version has only around 490k parameters which is 3.5x reduction 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.

View on arXiv
@article{dmitrieva2025_2503.17141,
  title={ HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks },
  author={ Ekaterina Dmitrieva and Maksim Kaledin },
  journal={arXiv preprint arXiv:2503.17141},
  year={ 2025 }
}
Comments on this paper