Comments (3)
JasonSWFu
commented on September 26, 2024
Hi, all these numbers are based on their original papers. If the authors didn't report the number, I cannot obtain the results. The PESQ score of deep loss is roughly 2.51 according to this paper: https://arxiv.org/pdf/1908.08044.pdf
from metricgan.
byuns9334
commented on September 26, 2024
@JasonSWFu Hi, thanks for the reply . But are those numbers based on the same training/test set though?
from metricgan.
JasonSWFu
commented on September 26, 2024
Yes.
from metricgan.
Related Issues (15)
- 请问你们和“Training Supervised Speech Separation System to Improve STOI and PESQ Directly” 做过对比吗？ HOT 1
- ~loss: Nan HOT 3
- Batch Size = 1 HOT 1
- About target metric
- Multi GPU issue
- Questions about MetricGAN
- About pesq measurement
- 评价指标 HOT 9
- which cuda and cudnn version did you use? HOT 3
- method HOT 8
- A few question on training schemes HOT 2
- pretrained SE model available? HOT 2
- Is it possible to share detailly requriments?
- Running PESQ file HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from metricgan.