JunzheJosephZhu commited on
Commit
cc9bb5b
1 Parent(s): 5e0c846

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -13,6 +13,8 @@ license: cc-by-sa-4.0
13
  ## Description:
14
  - Code: The code corresponding to this pretrained model can be found [here](https://github.com/asteroid-team/asteroid/tree/master/egs/wsj0-mix-var/Multi-Decoder-DPRNN).
15
 
 
 
16
  - [Paper](http://www.isle.illinois.edu/speech_web_lg/pubs/2021/zhu2021multi.pdf): "Multi-Decoder DPRNN: High Accuracy Source Counting and Separation", Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson. ICASSP(2021).
17
 
18
  - Summary: This model achieves SOTA on the problem of source separation with an unknown number of speakers. It uses multiple decoder heads(each tackling a distinct number of speakers), in addition to a classifier head that selects which decoder head to use.
13
  ## Description:
14
  - Code: The code corresponding to this pretrained model can be found [here](https://github.com/asteroid-team/asteroid/tree/master/egs/wsj0-mix-var/Multi-Decoder-DPRNN).
15
 
16
+ - Notebook: Colab Notebook with examples can be found [here](https://colab.research.google.com/drive/11MGx3_sgOrQrB6k8edyAvg5mGIxqR5ED?usp=sharing)
17
+
18
  - [Paper](http://www.isle.illinois.edu/speech_web_lg/pubs/2021/zhu2021multi.pdf): "Multi-Decoder DPRNN: High Accuracy Source Counting and Separation", Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson. ICASSP(2021).
19
 
20
  - Summary: This model achieves SOTA on the problem of source separation with an unknown number of speakers. It uses multiple decoder heads(each tackling a distinct number of speakers), in addition to a classifier head that selects which decoder head to use.