Description: 改进PSO-SVM在说话人识别中的应用。通过对粒子群优化算法中惯性权重和全局最优值
的分析，提出了一种根据迭代次数而自适应变化的惯性权重的粒子群优化方法-Improvement in the PSO-SVM speaker recognition applications. Through particle swarm optimization algorithm in the inertia weight and the analysis of the global optimum value, a number of iterations in accordance with changes in the adaptive inertia weight particle swarm optimization method Platform: |
Size: 315392 |
Author:彭伟 |
Hits:
Description: 基于SVM的文本无关说话人识别算法研究，本文在最后用Matlab程序实现了一个基于支持向量机的说话人识别系统试验平台。并根据对参试者进行的大量身份测试试验，总结系统的各方面性能和分析存在的问题，为进一步研究提供了方向和宝贵的经验。
-SVM-based text independent speaker recognition algorithm, the paper used in the final implementation of a Matlab program based on support vector machine speaker recognition system test platform. And tested based on the identity of those who carried out a large number of test trials, summed up the system performance and analysis of all aspects of the problems, provide a direction for further research and valuable experience. Platform: |
Size: 1841152 |
Author:王伟 |
Hits:
Description: 建立了普通话语音性别数据库,提出联合梅尔频率频谱系数(Mel2f requency Cep st rum
Coefficient s , MFCC) 的特征提取方法和支持向量机(Support Vector Machine , SVM) 的分类方法进行说话人性别识别,并与其它分类方法进行比较。-A Chinese speech ( mandarin ) database was established for speaker s gender recognition. A
combination met hod is p roposed for gender recognition of speaker s based on support vector machine and
Mel2f requency cep st rum coefficient s (MFCC) for classification and feat ure ext raction respectively. Platform: |
Size: 303104 |
Author:wangqipeng |
Hits:
Description: 实现基于SVM的说话人识别，其算法比传统的svm有所改进，鲁棒性更强-SVM-based speaker recognition, and improvements in the algorithm than the traditional svm more robust Platform: |
Size: 3229696 |
Author:熊开芳 |
Hits:
Description: 调信息在汉语语音识别中具有非常重要的意义。采用支持向量机对连续汉语连续语音进行声调识别实
验，首先采用基于Teager能量算子和过零率的两级判别策略对连续语音进行浊音段提取，然后建立了适合于支持向
量机分类模型的等维声调特征向量。使用6个二类SVM模型对非特定人汉语普通话的4种声调进行分类识别，与
BP神经网络相比，支持向量杌具有更高的识别率。-Tone is an essential component for word formation in Chinese languages．It plays a very important role in the
transmission of information in speech communication．We looked at using support vector machines(SVMs)for auto—
matic tone recognition in continuously spoken Mandarin．The voiced segments were detected based on Teager Energy
Operation and ZCIL Compared with BP neural network。considerable improvement was achieved by adopting 6 binary-
SVMs scheme in a speaker-independent Mandarin tone recognition system． Platform: |
Size: 316416 |
Author:沈 |
Hits:
Description: 说话人识别算法SVM 全套可以运行，包含端点检测，特征提取等-Speaker recognition algorithm a full set of SVM can run, contains the endpoint detection, feature extraction Platform: |
Size: 9216 |
Author:刘黑 |
Hits:
Description: SVM支持向量机算法做语音识别的详细仿真实现代码,需要自己准备语音库，依次训练出模板，包含附加调用的函数库在内，欢迎和做语音识别，说话人识别的朋友交流-SVM support vector machine algorithm to do the detailed simulation of voice recognition to achieve the code, you need to prepare their own voice library, followed by training out of the template, including additional call function library, welcome and do voice recognition, speaker recognition friends exchange Platform: |
Size: 11264 |
Author:陈盛 |
Hits:
Search - speaker recognition SVM