Self-supervised speech denoising using only noisy audio signals (2021-10-30T00:00:00.000000Z)

TL;DR

Experimental results show that the proposed method not only eliminates the high dependence on clean targets of traditional audio denoising tasks, but also achieves on-par or better performance than other training strategies.

Authors

Lei Li

2 papers

Jiasong Wu

1 papers

Qingchun Li

1 papers

Guanyu Yang

1 papers

L. Senhadji

1 papers

H. Shu

1 papers

TL;DR

Authors

References46 items

Training Speech Enhancement Systems with Noisy Speech Datasets

CAUNet: Context-Aware U-Net for Speech Enhancement in Time Domain

Speech Denoising without Clean Training Data: a Noise2Noise Approach

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

Efficient Personalized Speech Enhancement Through Self-Supervised Learning

Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification

Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech

Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images

Training Noisy Single-Channel Speech Separation with Noisy Oracle Sources: A Large Gap and a Small Step

Real Time Speech Enhancement in the Waveform Domain

Unsupervised Sound Separation Using Mixture Invariant Training

Self-supervised Learning for Speech Enhancement

HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks

Densely Connected Neural Network with Dilated Convolutions for Real-Time Speech Enhancement in The Time Domain

PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network

Dual-Path RNN: Efficient Long Sequence Modeling for Time-Domain Single-Channel Speech Separation

T-GSA: Transformer with Gaussian-Weighted Self-Attention for Speech Enhancement

MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement

Sergan: Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty

Improving deep speech denoising by Noisy2Noisy signal mapping

Phase-aware Speech Enhancement with Deep Complex U-Net

Improved Speech Enhancement with the Wave-U-Net

Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech Separation

Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

Time-Frequency Masking-Based Speech Enhancement Using Generative Adversarial Network

Noise2Noise: Learning Image Restoration without Clean Data

End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networks

Noisy speech database for training speech enhancement algorithms and TTS models

Attention is All you Need

Deep Complex Networks

SEGAN: Speech Enhancement Generative Adversarial Network

DNN-based enhancement of noisy and reverberant speech

Complex Ratio Masking for Monaural Speech Separation

Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR

U-Net: Convolutional Networks for Biomedical Image Segmentation

A Dataset and Taxonomy for Urban Sound Research

The voice bank corpus: Design, collection and data analysis of a large regional accent speech database

Ideal ratio mask estimation using deep neural networks for robust speech recognition

The Diverse Environments Multi-channel Acoustic Noise Database (DEMAND): A database of multichannel environmental noise recordings

An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech

Subjective comparison and evaluation of speech enhancement algorithms

An Experimental Study on Speech Enhancement Based on Deep Neural Networks

Evaluation of Objective Quality Measures for Speech Enhancement

On binary and ratio time-frequency masks for robust speech recognition

Methods for objective and subjective assessment of quality Perceptual evaluation of speech quality ( PESQ ) : An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs

Webbie, M, 2018

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names