awesome-repositories.com
Blog
MCP
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
xiph avatar

xiph/rnnoise

0
View on GitHub↗

Rnnoise

rnnoise is a real-time speech denoising library that uses a recurrent neural network to suppress background noise from live voice audio. It is implemented as a lightweight C library with a minimal API, designed for easy integration into audio applications that need low-latency noise reduction.

The library employs a gated recurrent unit (GRU) architecture and frequency-domain feature extraction to capture temporal dependencies in speech, operating on short audio frames sequentially for streaming use. It also includes a training pipeline that allows users to train custom noise suppression models by combining clean speech and noise datasets, producing a neural network model tailored to specific noise environments.

The library supports real-time speech noise suppression for calls, conferencing, and recordings, as well as speech enhancement for pre-recorded audio production. Its custom model trainer generates training features from clean speech and noise data, enabling users to build their own denoising models.

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Features

  • Speech Denoisers - A C library for applying deep learning models to suppress environmental noise in speech streams with low latency.
  • Real-Time Audio Filters - Processes short audio frames sequentially with low latency for real-time streaming noise suppression.
  • Gated Recurrent Units - Employs gated recurrent unit layers to capture temporal dependencies in speech for effective noise reduction.
  • Audio Spectral Features - Extracts frequency-domain spectral features from audio for input into the neural network noise suppression model.
  • Audio Noise Suppression - Uses a trained recurrent neural network to filter non-speech components from audio frames in real time.
  • Neural Network Denoisers - Provides a neural network designed for enhancing speech quality by reducing non-speech sounds in real time.
  • C Audio Libraries - Ships a lightweight C library with a minimal API for integrating real-time noise suppression into audio applications.
  • Noise Suppression Model Training - Generates training features from clean speech and noise data and produces a custom neural network model for noise suppression.
  • Custom Noise Suppression Model Training Pipelines - Provides a training pipeline that generates features from clean speech and noise data to produce custom noise suppression models.
  • Speech Enhancers - Applies neural noise suppression to pre-recorded speech tracks to remove unwanted background noise before publishing.
  • Custom Model Trainers - Ships a tool for training user-specific neural network noise suppression models from clean speech and noise datasets.
  • Real-Time Voice and Video Communication - Cleans up speech audio in real-time to improve intelligibility and comfort during voice calls or conferencing.
  • Model Optimization - Hybrid DSP and deep learning for real-time speech enhancement.
  • Speech Enhancement Models - Real-time noise suppression using recurrent neural networks.
  • Audio - Neural network-based audio noise reduction.
  • Audio Processing - Neural network-based audio noise reduction.
  • Audio Processing and Analysis - RNN-based real-time noise suppression library for speech.
  • Noise reduction - Listed in the “Noise reduction” section of the Ailia Models awesome list.
5,368 stele·1,039 fork-uri·C·bsd-3-clause·8 vizualizări

Istoric stele

Graficul istoricului de stele pentru xiph/rnnoiseGraficul istoricului de stele pentru xiph/rnnoise

Întrebări frecvente

Ce face xiph/rnnoise?

rnnoise is a real-time speech denoising library that uses a recurrent neural network to suppress background noise from live voice audio. It is implemented as a lightweight C library with a minimal API, designed for easy integration into audio applications that need low-latency noise reduction.

Care sunt principalele funcționalități ale xiph/rnnoise?

Principalele funcționalități ale xiph/rnnoise sunt: Speech Denoisers, Real-Time Audio Filters, Gated Recurrent Units, Audio Spectral Features, Audio Noise Suppression, Neural Network Denoisers, C Audio Libraries, Noise Suppression Model Training.

Care sunt câteva alternative open-source pentru xiph/rnnoise?

Alternativele open-source pentru xiph/rnnoise includ: aubio/aubio — Aubio is an audio analysis and digital signal processing library designed for music information retrieval. It provides… werman/noise-suppression-for-voice. mackron/miniaudio — miniaudio is a single-file C audio library used for audio playback, capture, and hardware interfacing across multiple… tyiannak/pyaudioanalysis — pyAudioAnalysis is a Python library and framework for audio signal processing and analysis. It provides tools for… rikorose/deepfilternet — DeepFilterNet is a deep learning noise suppression framework and real-time audio filter designed to isolate speech and… librosa/librosa — Librosa is a Python audio analysis library and digital signal processing framework. It functions as a feature…

Alternative open-source pentru Rnnoise

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Rnnoise.
  • aubio/aubioAvatar aubio

    aubio/aubio

    3,714Vezi pe GitHub↗

    Aubio is an audio analysis and digital signal processing library designed for music information retrieval. It provides a suite of tools for extracting musical features, estimating fundamental frequencies, and tracking rhythmic pulses in audio streams. The library specializes in the detection of pitch and beat, enabling the extraction of musical notes and the estimation of overall tempo. It also includes capabilities for automatic onset detection to identify the start of sonic events and the separation of audio signals into percussive transients and steady-state tonal components. The system c

    Canalysisannotationaudio
    Vezi pe GitHub↗3,714
  • werman/noise-suppression-for-voiceAvatar werman

    werman/noise-suppression-for-voice

    6,324Vezi pe GitHub↗
    C++au-pluginauv3-pluginladspa
    Vezi pe GitHub↗6,324
  • tyiannak/pyaudioanalysisAvatar tyiannak

    tyiannak/pyAudioAnalysis

    6,242Vezi pe GitHub↗

    pyAudioAnalysis is a Python library and framework for audio signal processing and analysis. It provides tools for extracting mathematical representations of sound, such as spectrograms, and implements a system for training and evaluating machine learning models to classify audio segments based on acoustic patterns. The project includes dedicated utilities for audio segmentation, which allow for the removal of silence and the detection of specific audio events to divide recordings into meaningful sections. It also provides data visualization capabilities that use dimensionality reduction to ma

    Python
    Vezi pe GitHub↗6,242
  • mackron/miniaudioAvatar mackron

    mackron/miniaudio

    6,905Vezi pe GitHub↗

    miniaudio is a single-file C audio library used for audio playback, capture, and hardware interfacing across multiple operating systems. It functions as an audio hardware abstraction layer, an audio processing engine, an audio synthesis engine, and a codec and resampler. The project implements a node-graph based system for routing digital audio signals, mixing, and 3D spatialization. It also includes a programmatic generator for noise patterns and basic waveforms used for sound creation and signal testing. The library covers digital signal processing, including audio format conversion and sa

    C
    Vezi pe GitHub↗6,905
Vezi toate cele 30 alternative pentru Rnnoise→