This is the Linux app named Denoiser whose latest release can be downloaded as denoiserv0.1.4sourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Denoiser with OnWorks for free.
Segui queste istruzioni per eseguire questa app:
- 1. Scaricata questa applicazione sul tuo PC.
- 2. Entra nel nostro file manager https://www.onworks.net/myfiles.php?username=XXXXX con il nome utente che desideri.
- 3. Carica questa applicazione in tale file manager.
- 4. Avviare l'emulatore online OnWorks Linux o Windows online o l'emulatore online MACOS da questo sito Web.
- 5. Dal sistema operativo OnWorks Linux che hai appena avviato, vai al nostro file manager https://www.onworks.net/myfiles.php?username=XXXXX con il nome utente che desideri.
- 6. Scarica l'applicazione, installala ed eseguila.
IMMAGINI
Ad
Denoiser
DESCRIZIONE
Denoiser is a real-time speech enhancement model operating directly on raw waveforms, designed to clean noisy audio while running efficiently on CPU. It uses a causal encoder-decoder architecture with skip connections, optimized with losses defined both in the time domain and frequency domain to better suppress noise while preserving speech. Unlike models that operate on spectrograms alone, this design enables lower latency and coherent waveform output. The implementation includes data augmentation techniques applied to the raw waveforms (e.g. noise mixing, reverberation) to improve model robustness and generalization to diverse noise types. The project supports both offline denoising (batch inference) and live audio processing (e.g. via loopback audio interfaces), making it practical for real-time use in calls or recording. The codebase includes training and evaluation scripts, configuration management via Hydra, and pretrained models on standard noise datasets.
Caratteristiche
- Causal waveform-domain speech enhancement (no spectral inversion)
- Encoder-decoder architecture with skip connections for high fidelity
- Combined time-domain and frequency-domain loss optimization
- Raw waveform data augmentation to boost robustness against noise/reverb
- Support for live audio processing with low latency
- Training/evaluation scripts with pretrained models and config pipeline
Linguaggio di programmazione
Python
Categorie
This is an application that can also be fetched from https://sourceforge.net/projects/denoiser.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
