Primi Isolated Words Spectrogram Classification by Support Vector Machine Based on Immune Genetic Algorithm
| Autor: | Hua Yang, Wenlin Pan, Huazhen Dong, Mei-jun Fu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
0301 basic medicine
Computer science business.industry Short-time Fourier transform Pattern recognition 02 engineering and technology Immune genetic algorithm Support vector machine 03 medical and health sciences 030104 developmental biology Feature (computer vision) 0202 electrical engineering electronic engineering information engineering Spectrogram 020201 artificial intelligence & image processing Artificial intelligence business Spectrograph |
| Zdroj: | DEStech Transactions on Computer Science and Engineering. |
| ISSN: | 2475-8841 |
| DOI: | 10.12783/dtcse/aiie2017/18186 |
| Popis: | We propose a method for Primi isolated words spectrogram classification by support vector machine based on immune genetic algorithm (SVM-IGA). Firstly, time-frequency spectrograph of Primi isolated words is generated by Short Time Fourier Transform (STFT). Secondly, binary feature is extracted by binarization spectrogram. Thirdly, spectrogram classification is realized by IGA-SVM. The experimental results show that the predictive accuracy rate of Primi isolated words spectrogram classification was 88~91%. Compared with the speech signal classification, the spectrogram classification by SVM-IGA is better. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|