在模式识别领域,投票策略是非常有效的,而且已被成功应用到人脸检测、识别等领域.然而,在手写汉字识别(Handwritten Chinese character recognition,HCCR)中,由于类别集很大、训练样本少等特点,现有的很多分类器集成方法方法都很难直接...在模式识别领域,投票策略是非常有效的,而且已被成功应用到人脸检测、识别等领域.然而,在手写汉字识别(Handwritten Chinese character recognition,HCCR)中,由于类别集很大、训练样本少等特点,现有的很多分类器集成方法方法都很难直接应用于此领域.本文提出一种自产生式投票的方法,该方法通过事先学习得到的参数集产生一个测试集合,然后用一个分类器去识别测试集合中的每个样本,得到属于各个类别的概率,最后通过加权投票得到识别结果.实验结果表明,本文提出的方法是实用和有效的.展开更多
Quadratic Discrimination Function （QDF） is commonly used in speech emotion recognition, which proceeds on the premise that the input data is normal distribution. In this paper, we propose a transformation to normali...Quadratic Discrimination Function （QDF） is commonly used in speech emotion recognition, which proceeds on the premise that the input data is normal distribution. In this paper, we propose a transformation to normalize the emotional features, emotion recognition. Features based on prosody then derivate a Modified QDF （MQDF） to speech and voice quality are extracted and Principal Component Analysis Neural Network （PCANN） is used to reduce dimension of the feature vectors. The results show that voice quality features are effective supplement for recognition, and the method in this paper could improve the recognition ratio effectively.展开更多
文摘在模式识别领域,投票策略是非常有效的,而且已被成功应用到人脸检测、识别等领域.然而,在手写汉字识别(Handwritten Chinese character recognition,HCCR)中,由于类别集很大、训练样本少等特点,现有的很多分类器集成方法方法都很难直接应用于此领域.本文提出一种自产生式投票的方法,该方法通过事先学习得到的参数集产生一个测试集合,然后用一个分类器去识别测试集合中的每个样本,得到属于各个类别的概率,最后通过加权投票得到识别结果.实验结果表明,本文提出的方法是实用和有效的.
基金the Ministry of Education Fund (No: 20050286001)Ministry of Education "New Century Tal-ents Support Plan" (No:NCET-04-0483)Doctoral Foundation of Ministry of Education (No:20050286001).
文摘Quadratic Discrimination Function （QDF） is commonly used in speech emotion recognition, which proceeds on the premise that the input data is normal distribution. In this paper, we propose a transformation to normalize the emotional features, emotion recognition. Features based on prosody then derivate a Modified QDF （MQDF） to speech and voice quality are extracted and Principal Component Analysis Neural Network （PCANN） is used to reduce dimension of the feature vectors. The results show that voice quality features are effective supplement for recognition, and the method in this paper could improve the recognition ratio effectively.
基金This work was supported by the National Natural Science Foundation of China （No.60875006）, Program for Leading Talent of SEAC, and also was supported by Innovative Team Subsidize of Northwest University for Nationalities.
