MC_GRID (131934 files)
README.md 4.04kB
grid_vp.pkl 70.35MB
lip_fea/test/s12/bbae1n.npy 76.93kB
lip_fea/test/s12/bbae2s.npy 76.93kB
lip_fea/test/s12/bbae3p.npy 76.93kB
lip_fea/test/s12/bbae4a.npy 76.93kB
lip_fea/test/s12/bbak5n.npy 76.93kB
lip_fea/test/s12/bbak6s.npy 76.93kB
lip_fea/test/s12/bbak7p.npy 76.93kB
lip_fea/test/s12/bbak8a.npy 76.93kB
lip_fea/test/s12/bbaq9n.npy 76.93kB
lip_fea/test/s12/bbar1p.npy 76.93kB
lip_fea/test/s12/bbar2a.npy 76.93kB
lip_fea/test/s12/bbarzs.npy 76.93kB
lip_fea/test/s12/bbay3n.npy 76.93kB
lip_fea/test/s12/bbay4s.npy 76.93kB
lip_fea/test/s12/bbay5p.npy 76.93kB
lip_fea/test/s12/bbay6a.npy 76.93kB
lip_fea/test/s12/bbbe5n.npy 76.93kB
lip_fea/test/s12/bbbe6s.npy 76.93kB
lip_fea/test/s12/bbbe7p.npy 76.93kB
lip_fea/test/s12/bbbe8a.npy 76.93kB
lip_fea/test/s12/bbbk9n.npy 76.93kB
lip_fea/test/s12/bbbl1p.npy 76.93kB
lip_fea/test/s12/bbbl2a.npy 76.93kB
lip_fea/test/s12/bbblzs.npy 76.93kB
lip_fea/test/s12/bbbr3n.npy 76.93kB
lip_fea/test/s12/bbbr4s.npy 76.93kB
lip_fea/test/s12/bbbr5p.npy 76.93kB
lip_fea/test/s12/bbbr6a.npy 76.93kB
lip_fea/test/s12/bbby7n.npy 76.93kB
lip_fea/test/s12/bbby8s.npy 76.93kB
lip_fea/test/s12/bbby9p.npy 76.93kB
lip_fea/test/s12/bbbzza.npy 76.93kB
lip_fea/test/s12/bbid7n.npy 76.93kB
lip_fea/test/s12/bbid8s.npy 76.93kB
lip_fea/test/s12/bbid9p.npy 76.93kB
lip_fea/test/s12/bbieza.npy 76.93kB
lip_fea/test/s12/bbik1n.npy 76.93kB
lip_fea/test/s12/bbik2s.npy 76.93kB
lip_fea/test/s12/bbik3p.npy 76.93kB
lip_fea/test/s12/bbik4a.npy 76.93kB
lip_fea/test/s12/bbiq5n.npy 76.93kB
lip_fea/test/s12/bbiq6s.npy 76.93kB
lip_fea/test/s12/bbiq7p.npy 76.93kB
lip_fea/test/s12/bbiq8a.npy 76.93kB
lip_fea/test/s12/bbix9n.npy 76.93kB
lip_fea/test/s12/bbiy1p.npy 76.93kB
lip_fea/test/s12/bbiy2a.npy 76.93kB
Too many files! Click here to view them all.
Type: Dataset
Tags: Speech Separation, Speaker Extraction

Bibtex:
@article{,
title= {MC_GRID},
journal= {},
author= {Qinghua Liu and Yating Huang and Yunzhe Hao and Jiaming Xu and Bo Xu},
year= {},
url= {},
abstract= {Here we release the dataset (Multi_Channel_Grid, abbreviated as MC_Grid) used in our paper LIMUSE: LIGHTWEIGHT MULTI-MODAL SPEAKER EXTRACTION.
MC_Grid, which is based on GRID dataset, includes multi-channel audio, extracted voiceprint and visual feature. And our code is available at https://github.com/aispeech-lab/LiMuSE.
Feel free to contact us if you have any questions or suggestions.},
keywords= {Speech Separation, Speaker Extraction},
terms= {},
license= {},
superseded= {}
}


Send Feedback