CAJ | 학술논문

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。
어음정감식별시어음식별중적중요분지,시화해인궤교호적기출이론。유우단일분류기재어음정감식별중적국한성,본문제출료은마이과부모형（HMM）화인공신경망락（ANN）상결합적방법,대고흥、량기、분노、비상、공구、평정륙충정감분별설계일개HMM모형,득도매충정감적최가필배서렬,연후이용ANN작위후험분류기대측시양본진행분류,통과량충분류기융합제고어음정감식별솔。재통과유도록음법건립적정감어음고적기출상진행료실험험증,실험결과표명식별솔유교대적제고。
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.