marlenezw commited on
Commit
86a0b16
ยท
1 Parent(s): bf0121b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -1,3 +1,12 @@
1
  ---
2
  license: cc-by-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
1
  ---
2
  license: cc-by-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - code
7
+ - audio
8
+ - voice
9
  ---
10
+
11
+ This model is used to extract the speaker-agnostic content representation of an audio file. The model leverages AutoVC from Qian et al. [2019]..
12
+ The AutoVC network utilizes an LSTM-based encoder that compresses the input audio into a compact representation (bottleneck) trained to abandon the original speaker identity but preserve content. In our case, we extract a content embedding A โˆˆ R๐‘‡ร—๐ท from AutoVC network, where ๐‘‡ is the total number of input audio frames, and ๐ท is the content dimension.