Description: 基于改进的隐马尔可夫和神经网络混合模型的语音识别-Based on an improved Hidden Markov and neural network hybrid model of voice recognition Platform: |
Size: 302080 |
Author:张大鹏 |
Hits:
Description: 摘要 : 在 MAT LAB环境下利用语音工具箱 Voice Box实现基于连续概率密度隐含马尔科夫模型的汉语语音识别系统。在
实时录音的情况下 , 利用该语音识别系统 , 不同的人对 20条 2～8个字的语音命令进行识别 , 准确率可达到 95 ％ , 识别时间
115～3 s , 实现了小词汇量连续语音的非特定人的实时识别。-Abstract: In the circumstances the use of MAT LAB toolbox Voice Box Voice realize implied probability density based on continuous Markov model of Chinese speech recognition system. In real-time recording, the use of the voice recognition systems, different people on the 20 2 ~ 8-word voice command recognition accuracy rate can reach 95 percent, identify the time 115 ~ 3 s, the realization of a small vocabulary continuous voice of the non-specific real-time identification of people. Platform: |
Size: 208896 |
Author:tz1985 |
Hits:
Description: 常用的说话人识别方法有模板匹配法、统计建模法、联接主义法(即人工神经网络实现)。考虑到数据量、实时性以及识别率的问题，采用基于矢量量化和隐马尔可夫模型(HMM)相结合的方法。
说话人识别的系统主要由语音特征矢量提取单元(前端处理)、训练单元、识别单元和后处理单元组成，
-Commonly used methods of speaker recognition template matching method, statistical modeling method, and connection method (ie, artificial neural networks). Taking into account the amount of data, real-time as well as the recognition rate of the problem, based on vector quantization and Hidden Markov Model (HMM) method of combining. Speaker recognition system mainly by the voice feature vector extraction unit (front-end treatment), training modules, identification and post-treatment unit modules, Platform: |
Size: 64512 |
Author:孙丽 |
Hits:
Search - voice recognition matlab markov