Audio-Visual Speech Enhancement with Score-Based Generative Models
This website contains audio examples to the paper:
Julius Richter, Simone Frintrop, Timo Gerkmann, "Audio-Visual Speech Enhancement with Score-Based Generative Models", ITG Speech Communication, Aachen, Germany, Sep. 2023.
File
Clean
Noisy
SGMSE+ [1]
AV-Gen (ours)
zjnesmhixq0-00047
pslblz3hqkc-00001
qeirdqu0o9s-00002
tdafwnoikve-00004
v1yw5isnsjo-00003
rim5asvankg-00002
yzgjo5ahshq-00002
8nt3edwlgig-00005
ddxhlkiuhqg-00002
f3ohcpksubc-00006
fxtsmzkmdes-00017
tgzmsmcuixm-00013
gsf6nijssda-00007
gvfgkfaswn4-00003
jssc7hyksti-00019
liuclsitcy0-00001
[1] Julius Richter, Simon Welker, Jean-Marie Lemercier, Bunlong Lay, Timo Gerkmann. "Speech Enhancement and Dereverberation with Diffusion-Based Generative Models", IEEE/ACM Trans. Audio, Speech, Language Proc., 2023, accepted.