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.
P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge
Robust One-step Speech Enhancement via Consistency Distillation
Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement
EDNet: A Distortion-Agnostic Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training
A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments
Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
Exploring Length Generalization For Transformer-based Speech Enhancement
Neural Spectral Band Generation for Audio Coding
French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement
Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency
Lessons Learned from the URGENT 2024 Speech Enhancement Challenge
A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement
Learning to Upsample and Upmix Audio in the Latent Domain
A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement
Interspeech 2025 URGENT Speech Enhancement Challenge
DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need
ARiSE: Auto-Regressive Multi-Channel Speech Enhancement
Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement
Model as Loss: A Self-Consistent Training Paradigm
Stack Less, Repeat More: A Block Reusing Approach for Progressive Speech Enhancement
FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
Training-Free Multi-Step Audio Source Separation
Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement
A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions
TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network
UBGAN: Enhancing Coded Speech with Blind and Guided Bandwidth Extension
Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation
Improving Noise Robustness of LLM-based Zero-shot TTS via Discrete Acoustic Token Denoising
A Semantic Information-based Hierarchical Speech Enhancement Method Using Factorized Codec and Diffusion Model
RoVo: Robust Voice Protection Against Unauthorized Speech Synthesis with Embedding-Level Perturbations
MDDM: A Multi-view Discriminative Enhanced Diffusion-based Model for Speech Enhancement
Unified Architecture and Unsupervised Speech Disentanglement for Speaker Embedding-Free Enrollment in Personalized Speech Enhancement
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.