基于免疫遗传优化支持向量机的普米语孤立词语谱图分类 |
| |
作者单位: | ;1.云南民族大学数学与计算机科学学院;2.云南民族大学云南省高校物联网应用技术重点实验室 |
| |
摘 要: | 基于免疫遗传优化支持向量机的普米语孤立词语谱图分类方法,首先利用短时傅里叶变(STFT)生成普米语孤立词语谱图;其次,提取普米语孤立词语谱图的二值特征;最后,利用免疫遗传优化支持向量机实现语谱图的分类.实验结果表明:普米语孤立词语谱图分类预测准确率为88%~91%.基于免疫遗传优化支持向量机的语谱图分类比基于语音信号分类效果更好.
|
关 键 词: | 普米语 语谱图 支持向量机(SVM) 免疫遗传算法(IGA) 2值特征 |
Spectrogram-based classification of the Primi isolated words by the support vector machine based on an immune genetic algorithm |
| |
Institution: | ,School of Mathematics and Computer Sciences,Yunnan Minzu University,Key Laboratory of IOT Application Technology of Universities in Yunnan Province,Yunnan Minzu University |
| |
Abstract: | A method for the spectrogram-based classification of the Primi isolated words by the support vector machine based on an immune genetic algorithm( SVM-IGA) was proposed. Firstly,a time-frequency spectrograph of the Primi isolated words is generated by the Short-time Fourier Transform( STFT). Secondly,its binary feature is extracted. Thirdly,the spectrogram-based classification is realized by IGA-SVM. The experimental results show that the predictive accuracy rate of the spectrogram-based classification of the Primi isolated words is 88 ~ 91%.Compared with the speech signal classification,the spectrogram-based classification by SVM-IGA is better. |
| |
Keywords: | the Primi language spectrogram support vector machine(SVM) immune genetic algorithm(IGA) binary feature |
|