Implementation of artificial neural network to recognize numbers from voice
Speech recognition is a subjective phenomenon which also an important part of human–machine interaction which still faces a lot of problem. The purpose of this work is to investigate and apply the artificial neural network (ANN) to recognise numbers using voice. In this work, MATLAB neural network t...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Subjects: | |
| Online Access: | http://umpir.ump.edu.my/id/eprint/39528/1/Implementation%20of%20Artificial%20Neural%20Network%20to%20Recognize%20Numbers.pdf http://umpir.ump.edu.my/id/eprint/39528/2/Implementation%20of%20arti%EF%AC%81cial%20neural%20network%20to%20recognize%20numbers%20from%20voice_ABS.pdf http://umpir.ump.edu.my/id/eprint/39528/ https://doi.org/10.1007/978-981-16-8690-0_78 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Speech recognition is a subjective phenomenon which also an important part of human–machine interaction which still faces a lot of problem. The purpose of this work is to investigate and apply the artificial neural network (ANN) to recognise numbers using voice. In this work, MATLAB neural network toolbox is used to create, train and simulate the ANN. The dataset consisted a voice from ‘one’ to ‘five’ undergo windowing process to view a short time segment of a longer signal and analyse its frequency content and then being filtered by using a band-pass filter to remove the unwanted noise and been converted into histograms as an input for the network. From the experiments, the highest accuracy level obtained is 72.5% by using histograms as Feature Extraction. |
|---|