| 语音信号的主分量特征 |
| |
| 引用本文： | 何振亚 顾明亮. 语音信号的主分量特征[J]. 应用科学学报, 1999, 17(4): 427-437 |
| |
| 作者姓名： | 何振亚 顾明亮 |
| |
| 作者单位： | 东南大学 |
| |
| 基金项目： | 国家攀登计划认知科学中神经网络理论与应用基础研究重大关键资助 |
| |
| 摘 要： | 利用曲线拟合与主分量神经网络相结合的方法，提出了一种既反映声道变化符合人耳听觉特点和语音识别新特征。与其他神经网络识别特相比，新特征不仅可以提高语音识别准确率，而且具有算法简单，存储容量小，便于实时实现的特点。
|
| 关 键 词： | 主分量分析 特征提取 语音识别 语音信号 |
Principal Component Feature for Speech Recognition |
| |
| HE ZHENYA GU MINGLIANG WANG TAIJUN SHIXIAOXING. Principal Component Feature for Speech Recognition[J]. Journal of Applied Sciences, 1999, 17(4): 427-437 |
| |
| Authors: | HE ZHENYA GU MINGLIANG WANG TAIJUN SHIXIAOXING |
| |
| Abstract: | Using curve fitting and principalcom ponentanalysis m ethod, this paperpre- sents a novelANN-based speech recognition feature. The feature reflects the variation ofvocaltractw ith tim e. The extraction m ethod sim ulates the processing ofspeech in- form ation in hum an auditory system . Com pared with otherANN-based recognition fea- tures, thisnew featurenotonly increasetherecognition accuracy butalso has follow ing properties: lesscom plex algorithm , lessstoragem em ory and easy realization w ith hard- w are. |
| |
| Keywords: | principalcom ponent analysis neuralnetwork feature extraction speech recognition |
| 本文献已被 CNKI 维普 等数据库收录！ |
