https://github.com/jjunak-yun/FLowHigh_code
공식 코드FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single-Step Flow Matching
Papers with Code 아카이브
Speech Enhancement
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/joanne-b-nortier/udiffse
공식 코드Unsupervised speech enhancement with diffusion-based generative models
https://github.com/jusperlee/apollo
공식 코드Apollo: Band-sequence Modeling for High-Quality Audio Restoration
https://github.com/jusperlee/sonicsim
공식 코드SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
https://github.com/jwr1995/dtcn
공식 코드Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
https://github.com/jwr1995/wd-tcn
공식 코드https://github.com/jwr1995/whamr_ext
공식 코드Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation
https://github.com/jywanng/lbccn
공식 코드A Lightweight and Real-Time Binaural Speech Enhancement Model with Spatial Cues Preservation
https://github.com/jzhangu/basen
공식 코드https://github.com/kagaminccino/LAVSE
공식 코드https://github.com/khhungg/BSSE-SE
공식 코드https://github.com/kuray107/s4nd-u-net_speech_enhancement
공식 코드https://github.com/l3das/L3DAS21
공식 코드L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing
https://github.com/l3das/l3das22
공식 코드L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment
https://github.com/lamomal/multisv
공식 코드MultiSV: Dataset for Far-Field Multi-Channel Speaker Verification
https://github.com/lc-zhou/mask-fusion
공식 코드Masks Fusion with Multi-Target Learning For Speech Enhancement
https://github.com/leto19/commonvoice-demand
공식 코드https://github.com/line/open-universe
공식 코드Universal Score-based Speech Enhancement with High Content Preservation
https://github.com/littleflyingsheep/tsegan
공식 코드Time-domain Speech Enhancement with Generative Adversarial Learning
https://github.com/lucas-dunker/stem-separator-amt
공식 코드https://github.com/madhavmk/Noise2Noise-audio_denoising_without_clean_training_data
공식 코드Speech Denoising Without Clean Training Data: A Noise2Noise Approach
https://github.com/max1wz/h-gtcrn
공식 코드A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions
https://github.com/merlresearch/tf-locoformer
공식 코드TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement
https://github.com/michalsvento/NLDistortionDiff
공식 코드Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion
https://github.com/microsoft/AEC-Challenge
공식 코드https://github.com/microsoft/DNS-Challenge
공식 코드https://github.com/microsoft/P.808
공식 코드Multi-dimensional Speech Quality Assessment in Crowdsourcing
https://github.com/microsoft/aura
공식 코드Aura: Privacy-preserving Augmentation to Improve Test Set Diversity in Speech Enhancement
https://github.com/microsoft/speecht5
공식 코드SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing
https://github.com/minseon-gwak/speech-enhancement-zoom-phone
공식 코드Speech Enhancement for Virtual Meetings on Cellular Networks
https://github.com/mmmmayi/pl-eesr
공식 코드PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction
https://github.com/modelscope/ClearerVoice-Studio
공식 코드https://github.com/mtanveer1/avsec-3-challenge
공식 코드LSTMSE-Net: Long Short Term Speech Enhancement Network for Audio-visual Speech Enhancement
https://github.com/muqiaoy/PAAP
공식 코드PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement
https://github.com/muqiaoy/egemaps_estimator
공식 코드Improving Speech Enhancement through Fine-Grained Speech Characteristics
https://github.com/naplab/Conv-TasNet
공식 코드Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.