https://github.com/Xiaobin-Rong/ul-unas
공식 코드UL-UNAS: Ultra-Lightweight U-Nets for Real-Time Speech Enhancement via Network Architecture Search
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/ahmadikalkhorani/AVCrossNet
공식 코드https://github.com/ai4bharat/indicvoices-r
공식 코드IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
https://github.com/aircarlo/bin2bin-gan-plc
공식 코드A Time-Frequency Generative Adversarial based method for Audio Packet Loss Concealment
https://github.com/aleXiehta/PhoneFortifiedPerceptualLoss
공식 코드https://github.com/aleXiehta/WaveCRN
공식 코드WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
https://github.com/alexiehta/causal-se
공식 코드Inference and Denoise: Causal Inference-based Neural Speech Enhancement
https://github.com/alimmat/bss-cffma
공식 코드https://github.com/andreevp/wvmos
공식 코드HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
https://github.com/anicolson/DeepXi
공식 코드Deep Xi as a Front-End for Robust Automatic Speech Recognition
https://github.com/anton-jeran/MESH2IR
공식 코드MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
https://github.com/archiki/Robust-E2E-ASR
공식 코드An Investigation of End-to-End Models for Robust Speech Recognition
https://github.com/ashivdhondea/dfts2
공식 코드DFTS2: Simulating Deep Feature Transmission Over Packet Loss Channels
https://github.com/audio-agi/audiosep
공식 코드https://github.com/audio-westlakeu/fullsubnet
공식 코드https://github.com/audio-westlakeu/mcnet
공식 코드McNet: Fuse Multiple Cues for Multichannel Speech Enhancement
https://github.com/audio-westlakeu/mel-mcnet
공식 코드Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement
https://github.com/audio-westlakeu/rvae-em
공식 코드https://github.com/audiolabs/DEISM
공식 코드https://github.com/balkce/doacorrection
공식 코드Direction of Arrival Correction through Speech Quality Feedback
https://github.com/bepierre/SpeechVGG
공식 코드Word-level Embeddings for Cross-Task Transfer Learning in Speech Processing
https://github.com/bosecorp/devo
공식 코드Self-Supervised Learning for Speech Enhancement through Synthesis
https://github.com/caoruitju/rui_se
공식 코드A Refining Underlying Information Framework for Monaural Speech Enhancement
https://github.com/changlee0903/d4am
공식 코드D4AM: A General Denoising Framework for Downstream Acoustic Models
https://github.com/claritychallenge/clarity/tree/main/recipes/cpc1/e032_sheffield
공식 코드https://github.com/cogmhear/Intelligibility-Oriented-Audio-Visual-Speech-Enhancement
공식 코드Towards Intelligibility-Oriented Audio-Visual Speech Enhancement
https://github.com/danmerry/advsarial_se
공식 코드https://github.com/danmic/av-se
공식 코드An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
https://github.com/deepakbaby/isegan
공식 코드iSEGAN: Improved Speech Enhancement Generative Adversarial Networks
https://github.com/dhimasryan/MOSA-Net-Cross-Domain
공식 코드Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features
https://github.com/dhimasryan/Zero_Shot_Model_Selection
공식 코드https://github.com/dmse4tts/dmse4tts
공식 코드Diffusion-Based Mel-Spectrogram Enhancement for Personalized Speech Synthesis with Found Data
https://github.com/donghoney0416/DeFTAN-II
공식 코드DeFTAN-II: Efficient Multichannel Speech Enhancement with Subgroup Processing
https://github.com/dr-pato/audio_visual_speech_enhancement
공식 코드Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments
https://github.com/dreadbird06/tso_vace_wpe
공식 코드https://github.com/eloimoliner/babe2
공식 코드A Diffusion-Based Generative Equalizer for Music Restoration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.