文件列表:

LICENSE (1079, 2022-01-13)
config/ (0, 2022-01-13)
config/NN_BSS.yml (6010, 2022-01-13)
config/REVERB_2MIX.yml (1687, 2022-01-13)
criterion.py (5455, 2022-01-13)
dataloader/ (0, 2022-01-13)
dataloader/REVERB_2MIX.py (8592, 2022-01-13)
dataloader/RIR_mixing.py (8268, 2022-01-13)
dataloader/SMS_WSJ.py (15297, 2022-01-13)
dataloader/data.py (27581, 2022-01-13)
libs/ (0, 2022-01-13)
libs/audio.py (487, 2022-01-13)
model.py (25060, 2022-01-13)
requirement.sh (246, 2022-01-13)
requirements.txt (52, 2022-01-13)
run.py (17547, 2022-01-13)
sample/ (0, 2022-01-13)
sample/Beamforming/ (0, 2022-01-13)
sample/Beamforming/3_441c040w_445c040o_0.wav (192222, 2022-01-13)
sample/Beamforming/3_441c040w_445c040o_1.wav (192222, 2022-01-13)
sample/Clean/ (0, 2022-01-13)
sample/Clean/3_441c040w_445c040o_0.wav (1537536, 2022-01-13)
sample/Clean/3_441c040w_445c040o_1.wav (1537536, 2022-01-13)
sample/MISO1/ (0, 2022-01-13)
sample/MISO1/3_441c040w_445c040o_0.wav (192222, 2022-01-13)
sample/MISO1/3_441c040w_445c040o_1.wav (192222, 2022-01-13)
sample/MISO3/ (0, 2022-01-13)
sample/MISO3/3_441c040w_445c040o_0.wav (192222, 2022-01-13)
sample/MISO3/3_441c040w_445c040o_1.wav (192222, 2022-01-13)
tester.py (62834, 2022-01-13)
train.sh (373, 2022-01-13)
trainer.py (26720, 2022-01-13)
utils/ (0, 2022-01-13)
utils/plotting.py (977, 2022-01-13)
utils/writer.py (6944, 2022-01-13)

# MISOnet Unofficial Pytorch Multi-microphone complex spectral mapping for utterance-wise and continuous speech separation(MISO-BF-MISO) https://arxiv.org/abs/2010.01703 ## Todo - [x] MISO1 implementation (seperation Network) - [x] Speaker Alignment System - [x] MVDR implementation - [x] MISO3 implementatino (enhancement Network) - [ ] Speaker counting Network - [x] SMS-WSJ Dataset generation - [ ] LibriCSS Dataset generation ## Requirements - Python>=3.8.0 - Pytorch>=1.10.0 - (optional) virtualenv ## Training 0. (Optional) Setup Virtualenv ``` sudo pip3 install virtualenv virtualenv -p python3 venv source venv/bin/activate ``` 1. Setup python packages environments ``` pip install -r requirements.txt ``` 2. Run (todo) ``` python run.py --config=./config ``` 3. Spectrogram # Example of 3_441c040w_445c040o_0.wav amoung test_eval92 (sms_wsj) - Obervation - Clean Source 1 & 2 - MISO1 Model Output Source 1 & 2 - MVDR Beamformer Output Source 1 & 2 - MISO3 Model Output Source 1 & 2 ## Reference https://github.com/kaituoxu/Conv-TasNet https://github.com/fgnt/sms_wsj https://github.com/chenzhuo1011/libri_css

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：