https://github.com/speechLabBcCuny/onssen
공식 코드Onssen: an open-source speech separation and enhancement library
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/speechbrain/speechbrain
공식 코드https://github.com/speechbrain/speechbrain/tree/develop/recipes/REAL-M/sisnr-estimation
공식 코드https://github.com/speechbrain/speechbrain/tree/develop/recipes/WSJ0Mix/separation
공식 코드https://github.com/spkgyk/RTFS-Net
공식 코드RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
https://github.com/spkgyk/TDFNet
공식 코드TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion
https://github.com/stwisdom/dr-nmf
공식 코드Deep Recurrent NMF for Speech Separation by Unfolding Iterative Thresholding
https://github.com/sunits/Reverberated_WSJ_2MIX
공식 코드https://github.com/vb000/lookoncetohear
공식 코드Look Once to Hear: Target Speech Hearing with Noisy Examples
https://github.com/victorletzelter/annealed_mcl
공식 코드Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
https://github.com/vivjay30/Cone-of-Silence
공식 코드https://github.com/vysri/knowledge-boosting
공식 코드https://github.com/wanghelin1997/solospeech
공식 코드https://github.com/xi-j/Mamba-TasNet
공식 코드https://github.com/xi-j/mamba-asr
공식 코드https://github.com/yluo42/GC3
공식 코드Group Communication with Context Codec for Lightweight Source Separation
https://github.com/yluo42/TAC
공식 코드End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation
https://github.com/yuchen005/unified-enhance-separation
공식 코드https://github.com/zbang/usef-tse
공식 코드USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction
https://github.com/zexupan/seg
공식 코드https://huggingface.co/yipjiaqi/spgm
공식 코드SPGM: Prioritizing Local Features for enhanced speech separation performance
https://github.com/2024-MindSpore-1/Code3/tree/main/Sepformer
https://github.com/AkojimaSLP/Neural-mask-estimation
https://github.com/IliasDG/Demucs_Project
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
https://github.com/JuanFMontesinos/y-net
https://github.com/JunzheJosephZhu/Multi-Decoder-DPRNN
Multi-Decoder DPRNN: High Accuracy Source Counting and Separation
https://github.com/JusperLee/Conv-TasNet
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
https://github.com/JusperLee/Deep-Clustering-for-Speech-Separation
Deep clustering: Discriminative embeddings for segmentation and separation
https://github.com/JusperLee/Dual-Path-RNN-Pytorch
Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation
https://github.com/JusperLee/UtterancePIT-Speech-Separation
Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation
https://github.com/KMASAHIRO/DANet
Deep attractor network for single-microphone speaker separation
https://github.com/Mack189/gdprnn
Voice Separation with an Unknown Number of Multiple Speakers
https://github.com/MindCode-4/code-13/tree/main/WaveCRN-master
WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
https://github.com/MindSpore-scientific/code-2/tree/main/WaveCRN-master
WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement
https://github.com/Sanyuan-Chen/CSS_with_Conformer
https://github.com/Sanyuan-Chen/CSS_with_EETransformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.