Noise2Noise-audio_denoising_without_clean_training_data
Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". Paper accepted at the INTERSPEECH 2021 conference. This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing
Category
Voice enhancement
Type
Open source
Platform
Jupyter Notebook project
Pricing
Free / open source
License
MIT
GitHub stars
212
Last updated
2023-09-01
Top Noise2Noise-audio_denoising_without_clean_training_data alternatives
KrispAI noise and echo cancellation that sits between your mic and any calling app, plus call transcription features.NVIDIA BroadcastGPU-powered noise removal, room echo removal and virtual background for anyone with an RTX card.Adobe Podcast EnhanceUpload rough voice recordings and get studio-quality speech back — Adobe's free enhancement demo turned essential tool.AuphonicAutomated audio post-production: loudness normalization, leveling, noise reduction and encoding presets for podcasts.Waifu2x-Extension-GUIVideo, Image and GIF upscale/enlarge(Super-Resolution) and Video frame interpolation. Achieved with Waifu2x, Real-ESRGAN, Real-CUGAN, RTX VrnnoiseRecurrent neural network for audio noise reductionSee the full list of Noise2Noise-audio_denoising_without_clean_training_data alternatives →