HIGHLIGHTS
- Who: gerry from the Department of Computer Science and Information, Taibah, Medinah, Saudi Arabia have published the paper: Development of a Deep Learning-based Arabic Speech Recognition System for Automatons, in the Journal: (JOURNAL)
- How: In this study a vector of 128 MFCC features was used for each sample as it outperformed employing 10 20 40 80 120 and 200 MFCC features. The forget factor for the input dataset is calculated using an activation function with a sigmoid coefficient. The design of the model consists of two parts the encoder and the decoder. This study . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.