Speech Denoising

32 papers with code • 2 benchmarks • 3 datasets

Obtain the clean speech of the target speaker by suppressing the background noise.

Most implemented papers

WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing

microsoft/unilm 26 Oct 2021

Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks.

Speech Denoising with Deep Feature Losses

anicolson/DeepXi 27 Jun 2018

We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly.

WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement

aleXiehta/WaveCRN 6 Apr 2020

In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the temporal sequential property of the locality feature is modeled by stacked simple recurrent units (SRU).

Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation

bill9800/speech_separation 13 Feb 2015

In this paper, we explore joint optimization of masking functions and deep recurrent neural networks for monaural source separation tasks, including monaural speech separation, monaural singing voice separation, and speech denoising.

Speech Denoising Convolutional Neural Network trained with Deep Feature Losses.

francoisgermain/SpeechDenoisingWithDeepFeatureLosses Interspeech 2018

We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly.

Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses

modelscope/ClearerVoice-Studio 3 Feb 2021

In this paper, we propose a complex convolutional block attention module (CCBAM) to boost the representation power of the complex-valued convolutional layers by constructing more informative features.

Speech Denoising Without Clean Training Data: A Noise2Noise Approach

madhavmk/Noise2Noise-audio_denoising_without_clean_training_data 8 Apr 2021

This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.

FRA-RIR: Fast Random Approximation of the Image-source Method

yluo42/fra-rir 8 Aug 2022

The training of modern speech processing systems often requires a large amount of simulated room impulse response (RIR) data in order to allow the systems to generalize well in real-world, reverberant environments.

CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement

ruizhecao96/cmgan 22 Sep 2022

Rather than focusing exclusively on the speech denoising task, we extend this work to address the dereverberation and super-resolution tasks.

Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization

mohammadiha/bnmf 15 Sep 2017

We propose a novel speech enhancement method that is based on a Bayesian formulation of NMF (BNMF).