| 改进脉冲耦合神经网络的语音识别研究 |
| |
| 引用本文： | 张晓俊,陶智,施晓敏,顾济华. 改进脉冲耦合神经网络的语音识别研究[J]. 计算机工程与应用, 2007, 43(8): 51-53 |
| |
| 作者姓名： | 张晓俊 陶智 施晓敏 顾济华 |
| |
| 作者单位： | 苏州大学,物理科学与技术学院,江苏,苏州,215006;苏州大学,物理科学与技术学院,江苏,苏州,215006;苏州大学,物理科学与技术学院,江苏,苏州,215006;苏州大学,物理科学与技术学院,江苏,苏州,215006 |
| |
| 摘 要： | 提出了一种改进脉冲耦合神经网络(IPCNN)实现语音识别的方法。首先利用IPCNN来快速提取语音的语谱图图像特征，然后由概率神经网络(PNN)辅助来识别语音。通过训练语音样本来构成语音识别库并建立综合识别系统。实验结果表明,本方法相对于单独使用PCNN和PNN识别率分别提高了22.7%和39.4%,达到92%的识别率。
|
| 关 键 词： | 脉冲耦合神经网络 概率神经网络 语谱图 语音识别 |
| 文章编号： | 1002-8331（2007）08-0051-03 |
| 收稿时间： | 2006-04-06 |
| 修稿时间： | 2006-08-01 |
Improved PCNN in speech recognition research |
| |
| ZHANG Xiao-jun,TAO Zhi,SHI Xiao-min,GU Ji-hua. Improved PCNN in speech recognition research[J]. Computer Engineering and Applications, 2007, 43(8): 51-53 |
| |
| Authors: | ZHANG Xiao-jun TAO Zhi SHI Xiao-min GU Ji-hua |
| |
| Affiliation: | School of Physical Science and Technology,Suzhou University,Suzhou,Jiangsu 215006,China |
| |
| Abstract: | The paper proposes a method to recognize speech by Improved Pulsed-Coupled Neural Network(IPCNN).IPCNN is first used to extract the feature of spectrogram,and is then with the assistance of Probabilistic Neural Network(PNN)to recognize speech.By training speech samples,speech identification databases are constructed,and the integrated recognition system is then built.The experiment results show that comparing with using the IPCNN and PNN alone,this method can increase the recognition rate by 22.7% and 39.4%.And it can attain recognition rate of 92%. |
| |
| Keywords: | Pulse-Coupled Neural Network(PCNN) Probabilistic Neural Network(PNN) spectrogram speech recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
|
