'Add Noise to Background for Voice Separation
I want to implement a voice separation project. Now, I got a voice dataset with no background noise and a dataset about noise, such as engine sound , horn sound. How can I add(I don't know is this action called "add") this noise to the clean data? The noise is not as long as the clean voice, so do I need to repeat the noise to make them the same length? Or there is a method or a module can do this?
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|