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/sp-uhh/sgmse-bbed

공식 코드

Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement

https://github.com/sp-uhh/sgmse_crp

공식 코드

Single and Few-step Diffusion for Generative Speech Enhancement

https://github.com/sp-uhh/uncertainty-se

공식 코드

Integrating Uncertainty into Neural Network-based Speech Enhancement

https://github.com/speechbrain/speechbrain

공식 코드

Exploring Self-Attention Mechanisms for Speech Separation

https://github.com/speechbrain/speechbrain/tree/develop/recipes/Voicebank

공식 코드

MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speech

https://github.com/speechbrain/speechbrain/tree/develop/recipes/Voicebank/enhance/MetricGAN

공식 코드

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

https://github.com/sunwookimiub/BLSH

공식 코드

Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation

https://github.com/tdietzen/INST-PSD

공식 코드

Instantaneous PSD Estimation for Speech Enhancement based on Generalized Principal Components

https://github.com/thuhcsi/fullsubnet-plus

공식 코드

FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

https://github.com/tvuong123/ModulationDomainLoss

공식 코드

A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement

https://github.com/udase-chime2023/jspsych-p.835-listening-test

공식 코드

Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge

https://github.com/urgent-challenge/urgent2024_analysis

공식 코드

Lessons Learned from the URGENT 2024 Speech Enhancement Challenge

https://github.com/uwjunqi/Tensor-Train-Neural-Network

공식 코드

Tensor-to-Vector Regression for Multi-channel Speech Enhancement based on Tensor-Train Network

https://github.com/uwjunqi/ttn-vqc

공식 코드

Exploiting Low-Rank Tensor-Train Deep Neural Networks Based on Riemannian Gradient Descent With Illustrations of Speech Processing

https://github.com/vikastokala/bcctn

공식 코드

Binaural Speech Enhancement Using Deep Complex Convolutional Transformer Networks

https://github.com/wangkenpu/rsrgan

공식 코드

Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition

https://github.com/wangtianrui/APC-SNR

공식 코드

A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement

https://github.com/wangtianrui/HGCN

공식 코드

HGCN: Harmonic gated compensation network for speech enhancement

https://github.com/winddori2002/MANNER

공식 코드

MANNER: Multi-view Attention Network for Noise Erasure

https://github.com/wngh1187/diff-sv

공식 코드

Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Models

https://github.com/xcyu-0903/rose

공식 코드

ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning

https://github.com/xiaomi-research/dasheng-denoiser

공식 코드

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders

https://github.com/xinmengxu/uformer

공식 코드

U-Former: Improving Monaural Speech Enhancement with Multi-head Self and Cross Attention

https://github.com/xiph/lpcnet

공식 코드

Real-Time Packet Loss Concealment With Mixed Generative and Predictive Model

https://github.com/yluo42/GC3

공식 코드

Group Communication with Context Codec for Lightweight Source Separation

https://github.com/yongyizang/trainingfreemultistepasr

공식 코드

Training-Free Multi-Step Audio Source Separation

https://github.com/yuchen005/dpsl-asr

공식 코드

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

https://github.com/yuchen005/gradient-remedy

공식 코드

Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition

https://github.com/yuchen005/nase

공식 코드

Noise-aware Speech Enhancement using Diffusion Probabilistic Model

https://github.com/yuchen005/unified-enhance-separation

공식 코드

Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation

https://github.com/yuguochencuc/db-aiat

공식 코드

Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement

https://github.com/yunyangzeng/taploss

공식 코드

TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement

https://github.com/yuwchen/CITISEN

공식 코드

CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application

https://github.com/yuwchen/baspro

공식 코드

BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithm

https://github.com/yuxi6842/crvae

공식 코드

Complex Recurrent Variational Autoencoder with Application to Speech Enhancement

https://github.com/yuyangLiu-1/RIR_Estimation_OMT_Barycenter

공식 코드

Room Impulse Response Estimation through Optimal Mass Transport Barycenters

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