https://github.com/eloimoliner/bwe_historical_recordings
공식 코드BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks
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/eloimoliner/cqtdiff
공식 코드https://github.com/emrys365/se-scaling
공식 코드Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech Enhancement
https://github.com/espnet/espnet
공식 코드ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding
https://github.com/espnet/espnet/tree/master/egs/chime6/asr1
공식 코드Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription
https://github.com/etzinis/fedenhance
공식 코드Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data
https://github.com/etzinis/unsup_speech_enh_adaptation
공식 코드RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing
https://github.com/facebookresearch/EasyComDataset
공식 코드https://github.com/facebookresearch/Noresqa
공식 코드NORESQA: A Framework for Speech Quality Assessment using Non-Matching References
https://github.com/facebookresearch/demucs
공식 코드https://github.com/facebookresearch/denoiser
공식 코드https://github.com/facebookresearch/ears_dataset
공식 코드EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation
https://github.com/facebookresearch/facestar
공식 코드Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis
https://github.com/facebookresearch/learning-audio-visual-dereverberation
공식 코드https://github.com/felixfuyihui/uformer
공식 코드https://github.com/felixperfler/stable-hybrid-auditory-filterbanks
공식 코드Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
https://github.com/fgnt/mms_msg
공식 코드MMS-MSG: A Multi-purpose Multi-Speaker Mixture Signal Generator
https://github.com/fgnt/nara_wpe
공식 코드Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System
https://github.com/fgnt/pb_chime5
공식 코드https://github.com/fgnt/speaker_reassignment
공식 코드https://github.com/gmkim90/AAS_enhancement
공식 코드Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition
https://github.com/google-research/seanet
공식 코드https://github.com/haoheliu/ssr_eval
공식 코드https://github.com/haoheliu/voicefixer
공식 코드VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration
https://github.com/haoxiangsnr/spiking-fullsubnet
공식 코드Towards Ultra-Low-Power Neuromorphic Speech Enhancement with Spiking-FullSubNet
https://github.com/honee-w/flowse
공식 코드FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
https://github.com/hsinyilin19/discriminator-constrained-optimal-transport-network
공식 코드Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport
https://github.com/huaidanquede/PrimeK-Net
공식 코드https://github.com/humanmllm/cogenav
공식 코드CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization
https://github.com/hyyan2k/lisennet
공식 코드LiSenNet: Lightweight Sub-band and Dual-Path Modeling for Real-Time Speech Enhancement
https://github.com/ifnspaml/perceptual-weighting-filter-loss
공식 코드A Perceptual Weighting Filter Loss for DNN Training in Speech Enhancement
https://github.com/iiscleap/DIHARD_2019_baseline_alltracks
공식 코드The Second DIHARD Diarization Challenge: Dataset, task, and baselines
https://github.com/ioyy900205/mfnet
공식 코드https://github.com/ishuangziling/sef-pnet
공식 코드https://github.com/jhauret/eben
공식 코드https://github.com/jhauret/vibravox
공식 코드Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.