HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 21 Mar 2025.
Builds on
21 of 31 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2017Squeeze-and-Excitation Networkscited by 4,789
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
- 2018SDR - half-baked or well done?cited by 423
- 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
- 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
- 2020Attention is All You Need in Speech Separationcited by 185
- 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
- 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
- 2020DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancementcited by 141
- 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
- 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
9 more
- 2020HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networkscited by 40
- 2021TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domaincited by 36
- 2020VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognitioncited by 32
- 2022FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancementcited by 29
- 2022SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separationcited by 16
- 2022Resource-Efficient Separation Transformercited by 11
- 2022FFC-SE: Fast Fourier Convolution for Speech Enhancementcited by 7
- 2021Multi-user VoiceFilter-Lite via Attentive Speaker Embeddingcited by 4
- 2024SICRN: Advancing Speech Enhancement through State Space Model and Inplace Convolution Techniquescited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.