Papers with Code 아카이브
Speech Separation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 19
- 보존된 평가 기록
- 128
The task of extracting all overlapping speech sources in a given mixed speech signal refers to the Speech Separation. Speech Separation is a special scenario of source separation problem, where the focus is only on the overlapping speech signal sources and other interferences such as music or noise signals are not the main concern of the study. A recent representative Github project can be referred to ClearerVoice-Studio.
Source: A Unified Framework for Speech Separation
Image credit: Speech Separation of A Target Speaker Based on Deep Neural Networks
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/JuanFMontesinos/Acappella-YNet
공식 코드https://github.com/JuanFMontesinos/VoViT
공식 코드VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer
https://github.com/JunzheJosephZhu/Identify-Speakers-in-Cocktail-Parties-with-E2E-Attention
공식 코드Identify Speakers in Cocktail Parties with End-to-End Attention
https://github.com/JusperLee/IIANet
공식 코드IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
https://github.com/JusperLee/S4M
공식 코드A Neural State-Space Model Approach to Efficient Speech Separation
https://github.com/JusperLee/TDANet
공식 코드An efficient encoder-decoder architecture with top-down attention for speech separation
https://github.com/NVIDIA/NeMo
공식 코드Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration
https://github.com/SherifAbdulatif/CMGAN
공식 코드CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement
https://github.com/ShiZiqiang/dual-path-RNNs-DPRNNs-based-speech-separation
공식 코드Speech Separation Based on Multi-Stage Elaborated Dual-Path Deep BiLSTM with Auxiliary Identity Loss
https://github.com/SungFeng-Huang/SSL-pretraining-separation
공식 코드Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
https://github.com/WangHelin1997/Fast-GeCo
공식 코드Noise-robust Speech Separation with Fast Generative Correction
https://github.com/Windstudent/Complex-MTASSNet
공식 코드https://github.com/Wufan0Willan/DIP
공식 코드Speech Separation with Pretrained Frontend to Minimize Domain Mismatch
https://github.com/Yip-Jia-Qi/codecformer
공식 코드https://github.com/ahmadikalkhorani/AVCrossNet
공식 코드https://github.com/aispeech-lab/LiMuSE
공식 코드https://github.com/aleXiehta/WaveCRN
공식 코드WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
https://github.com/andrasschin/SepMamba
공식 코드SepMamba: State-space models for speaker separation using Mamba
https://github.com/annie-gu/MVAEBasedBSE
공식 코드https://github.com/anton-jeran/MESH2IR
공식 코드MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
https://github.com/arraydps/arraydps
공식 코드ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
https://github.com/asteroid-team/asteroid/tree/master/egs/wsj0-mix-var/Multi-Decoder-DPRNN
공식 코드Multi-Decoder DPRNN: High Accuracy Source Counting and Separation
https://github.com/butspeechfit/ravdess2mix
공식 코드Analysis of impact of emotions on target speech extraction and speech separation
https://github.com/butspeechfit/speakerbeam
공식 코드https://github.com/chenzhuo1011/libri_css
공식 코드https://github.com/danmic/av-se
공식 코드An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation
https://github.com/dmlguq456/SepReformer
공식 코드Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
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/dr-pato/ssgd
공식 코드Low-Latency Speech Separation Guided Diarization for Telephone Conversations
https://github.com/dw-speech-separation/train-test-convtasnet
공식 코드An enhanced Conv-TasNet model for speech separation using a speaker distance-based loss function
https://github.com/egruttadauria98/sspavaldo
공식 코드Online speaker diarization of meetings guided by speech separation
https://github.com/ertug/mixcycle
공식 코드MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training
https://github.com/espnet/espnet
공식 코드https://github.com/etzinis/sudo_rm_rf
공식 코드Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
https://github.com/etzinis/two_step_mask_learning
공식 코드Two-Step Sound Source Separation: Training on Learned Latent Targets
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.