摘要
语音情感识别是语音识别中的重要分支,是和谐人机交互的基础理论。由于单一分类器在语音情感识别中的局限性,本文提出了隐马尔科夫模型(HMM)和人工神经网络(ANN)相结合的方法,对高兴、惊奇、愤怒、悲伤、恐惧、平静六种情感分别设计一个HMM模型,得到每种情感的最佳匹配序列,然后利用ANN作为后验分类器对测试样本进行分类,通过两种分类器融合提高语音情感识别率。在通过诱导录音法建立的情感语音库的基础上进行了实验验证,实验结果表明识别率有较大的提高。
Speech emotion recognition is not only an important part of speech recognition but also the basic theory of harmonious human-computer interaction.As a single classifier in the limitations of speech emotion recognition.In this paper,we put forward a method:the Combination of Hidden Markov Model (HMM) and Artificial Neural Network (ANN),for the six emotion of happy,surprise,anger,sad,fear and clam,we design six HMM model for every emotion,through this method,we have the best matching sequence of each emotion.Then,the posterior ANN classifier is used to classify the test samples,through the integration of two classifiers to improve speech emotion recognition rate.Based on the emotion speech database established by recording induced,the experimental results indicate that there is great elevation in the recognition rate.
出处
《电子测试》
2011年第8期33-35,87,共4页
Electronic Test
关键词
隐马尔科夫链
人工神经网络
语音情感识别
Hidden Markov Model
Artificial Neural Network
Speech Emotion Recognition