Commit
·
960e3c5
1
Parent(s):
85d1300
itemize
Browse files
README.md
CHANGED
|
@@ -13,8 +13,11 @@ inference: false
|
|
| 13 |
## Description:
|
| 14 |
Paper: "Multi-Decoder DPRNN: High Accuracy Source Counting and Separation",
|
| 15 |
Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson. ICASSP(2021). https://ieeexplore.ieee.org/document/9414205
|
|
|
|
| 16 |
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.
|
|
|
|
| 17 |
Demo Page: https://junzhejosephzhu.github.io/Multi-Decoder-DPRNN/
|
|
|
|
| 18 |
Original research repo is at https://github.com/JunzheJosephZhu/MultiDecoder-DPRNN
|
| 19 |
|
| 20 |
This model was trained by Joseph Zhu using the wsj0-mix-var/Multi-Decoder-DPRNN recipe in Asteroid.
|
|
|
|
| 13 |
## Description:
|
| 14 |
Paper: "Multi-Decoder DPRNN: High Accuracy Source Counting and Separation",
|
| 15 |
Junzhe Zhu, Raymond Yeh, Mark Hasegawa-Johnson. ICASSP(2021). https://ieeexplore.ieee.org/document/9414205
|
| 16 |
+
|
| 17 |
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.
|
| 18 |
+
|
| 19 |
Demo Page: https://junzhejosephzhu.github.io/Multi-Decoder-DPRNN/
|
| 20 |
+
|
| 21 |
Original research repo is at https://github.com/JunzheJosephZhu/MultiDecoder-DPRNN
|
| 22 |
|
| 23 |
This model was trained by Joseph Zhu using the wsj0-mix-var/Multi-Decoder-DPRNN recipe in Asteroid.
|