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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
An Empirical Study on the Impact of Positional Encoding in Transformer-based Monaural Speech Enhancement
On Speech Pre-emphasis as a Simple and Inexpensive Method to Boost Speech Enhancement
Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction
Noise-robust zero-shot text-to-speech synthesis conditioned on self-supervised speech-representation model with adapters
BS-PLCNet: Band-split Packet Loss Concealment Network with Multi-task Learning Framework and Multi-discriminators
FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation
A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model
Single-channel speech enhancement using learnable loss mixup
On real-time multi-stage speech enhancement systems
A Refining Underlying Information Framework for Monaural Speech Enhancement
Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios
A Deep Representation Learning-based Speech Enhancement Method Using Complex Convolution Recurrent Variational Autoencoder
SELM: Speech Enhancement Using Discrete Tokens and Language Models
Ultra Low Complexity Deep Learning Based Noise Suppression
ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning
Investigating the Design Space of Diffusion Models for Speech Enhancement
Diffusion-Based Speech Enhancement in Matched and Mismatched Conditions Using a Heun-Based Sampler
Distributed Speech Dereverberation Using Weighted Prediction Error
SEFGAN: Harvesting the Power of Normalizing Flows and GANs for Efficient High-Quality Speech Enhancement
Head Orientation Estimation with Distributed Microphones Using Speech Radiation Patterns
Subspace Hybrid MVDR Beamforming for Augmented Hearing
AV-RIR: Audio-Visual Room Impulse Response Estimation
D4AM: A General Denoising Framework for Downstream Acoustic Models
LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models
CheapNET: Improving Light-weight speech enhancement network by projected loss function
Cooperative Dual Attention for Audio-Visual Speech Enhancement with Facial Cues
Sparsity-Driven EEG Channel Selection for Brain-Assisted Speech Enhancement
How does end-to-end speech recognition training impact speech enhancement artifacts?
SE Territory: Monaural Speech Enhancement Meets the Fixed Virtual Perceptual Space Mapping
DPATD: Dual-Phase Audio Transformer for Denoising
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Single channel speech enhancement by colored spectrograms
Generative Pre-training for Speech with Flow Matching
LC-TTFS: Towards Lossless Network Conversion for Spiking Neural Networks with TTFS Coding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.