Comments (1)
gabrielmittag
commented on July 21, 2024
4
Hi,
Generally, there is no pre-processing needed. However, the model will judge too quiet or too loud signals as degraded and it will result in a lower MOS score. The ideal volume is an active speech level (ASL) of -26dBo (same as for PESQ/POLQA). So if you want to compare different devices but want to neglect the difference in loudness it might be a good idea to normalize the signals.
The attached Figure shows the average MOS prediction (over multiple files) for different active speech level values.
from nisqa.
Related Issues (20)
- Continuous metrics? HOT 4
- TTS naturalness prediction based on which model
- Could you tell me if the MOS rating is objective or subjective? HOT 4
- Full Reference or No Reference When Subjectively Rating a Speech HOT 1
- upper bound and larger bound inconsistent with step sign HOT 1
- Audio input requirements HOT 2
- pip package HOT 4
- CDUA device does not load the model HOT 2
- Interpertation of Different metrics HOT 1
- The predict result seems not reliable HOT 3
- License
- upper bound and larger bound inconsistent with step sign
- It seams slowly because of some functions running on CPU
- max window length error for most audio files HOT 1
- Utilizing finetuned weights
- mos_pred预测分数有些奇怪
- MOS prediction during runtime
- Error in loading the files using the folder name
- Why the CUDA is getting out of memory
- question about MOS_pred of synthetic speech
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 nisqa.