Papers with Code 아카이브

Speech Enhancement

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 4
평가표: 18
보존된 평가 기록: 122

Speech Enhancement is a signal processing task that involves improving the quality of speech signals captured under noisy or degraded conditions. The goal of speech enhancement is to make speech signals clearer, more intelligible, and more pleasant to listen to, which can be used for various applications such as voice recognition, teleconferencing, and hearing aids. A representative Github project with online demo : ClearerVoice-Studio.

<span style="color:grey; opacity: 0.6">( Image credit: A Fully Convolutional Neural Network For Speech Enhancement )</span>

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/ADDchallenge/SceneFake

공식 코드

SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detection

https://github.com/AdiCohen501/ExNet-BF-PF

공식 코드

Explainable DNN-based Beamformer with Postfilter

https://github.com/Audio-WestlakeU/CleanMel

공식 코드

CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

https://github.com/Audio-WestlakeU/VINP

공식 코드

VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification

https://github.com/BoseCorp/efficient-neural-speech-enhancement

공식 코드

TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

https://github.com/CedArctic/rnnoise-ex

공식 코드

RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features

https://github.com/ChangLee0903/SERIL

공식 코드

SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning

https://github.com/Chutlhu/dEchorate

공식 코드

dEchorate: a Calibrated Room Impulse Response Database for Echo-aware Signal Processing

https://github.com/ConferencingSpeech/ConferencingSpeech2021

공식 코드

INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing

https://github.com/Dahan-Wang/Adaptive-Convolution-for-CNN-based-Speech-Enhancement-Models

공식 코드

Adaptive Convolution for CNN-based Speech Enhancement Models

https://github.com/FrancoisGrondin/mvdrpf

공식 코드

PlumberNet: Fixing interference leakage after GEV beamforming

https://github.com/IU-SAIGE/contrastive_mixtures

공식 코드

Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement

https://github.com/IU-SAIGE/sparse_mle

공식 코드

Sparse Mixture of Local Experts for Efficient Speech Enhancement

https://github.com/JasonSWFu/Learning-with-Learned-Loss-Function

공식 코드

Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Quality

https://github.com/JasonSWFu/MetricGAN

공식 코드

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

https://github.com/JasonSWFu/VQscore

공식 코드

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech

https://github.com/JethroWangSir/NADA-GAN

공식 코드

Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation

https://github.com/K-STMLab/SSL4PR

공식 코드

Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions

https://github.com/KVDmitrieva/source_sep_hifi

공식 코드

HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks

https://github.com/Kevin-naticl/LLaSE-G1

공식 코드

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement

https://github.com/Li-Chongyi/Zero-DCE

공식 코드

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

https://github.com/LiangXu123/Robust-One-step-Speech-Enhancement-via-Consistency-Distillation-ROSE-CD-

공식 코드

Robust One-step Speech Enhancement via Consistency Distillation

https://github.com/ModarHalimeh/COSPA

공식 코드

Complex-valued Spatial Autoencoders for Multichannel Speech Enhancement

https://github.com/NVIDIA/NeMo

공식 코드

Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration

https://github.com/NikolaiKyhne/MambAttention

공식 코드

MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement

https://github.com/OSU-slatelab/mimic-enhance

공식 코드

Phonetic Feedback for Speech Enhancement With and Without Parallel Speech Data

https://github.com/Rikorose/clc-dns-challenge-2020

공식 코드

CLC: Complex Linear Coding for the DNS 2020 Challenge

https://github.com/SRPOL-AUI/storir

공식 코드

StoRIR: Stochastic Room Impulse Response Generation for Audio Data Augmentation

https://github.com/Screeen/SVD-direct

공식 코드

Wideband Relative Transfer Function (RTF) Estimation Exploiting Frequency Correlations

https://github.com/SherifAbdulatif/CMGAN

공식 코드

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

https://github.com/Sindhu-Hegde/pseudo-visual-speech-denoising

공식 코드

Visual Speech Enhancement Without A Real Visual Stream

https://github.com/Sinica-SLAM/Ny-EnhTT

공식 코드

A Training and Inference Strategy Using Noisy and Enhanced Speech as Target for Speech Enhancement without Clean Speech

https://github.com/SungFeng-Huang/SSL-pretraining-separation

공식 코드

Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training

https://github.com/Taltt/FNSE-SBGAN

공식 코드

FNSE-SBGAN: Far-field Speech Enhancement with Schrodinger Bridge and Generative Adversarial Networks

https://github.com/Wangfighting0015/GFT_project

공식 코드

Time-Graph Frequency Representation with Singular Value Decomposition for Neural Speech Enhancement

https://github.com/Windstudent/Complex-MTASSNet

공식 코드

Multi-Task Audio Source Separation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.