Title :
The hybrid model of affective recognition based on HMM and PNN
Author :
Jianing Tong ; Yahan Zhang
Author_Institution :
ShiJiaZhuang Vocational Technol. Inst., Shijiazhuang, China
Abstract :
Speech affective recognition is an important branch of speech recognition, whose main purpose is the emotional characteristics included in the analysis of speech signals. Because the use of a single model to identify which identify significant limitations. This paper presents a recognition model based on HMM and PNN, which using PNN for classification and using HMM for generating feature matching sequence. The experimental results show that high recognition rate in a single the HMM.
Keywords :
emotion recognition; feature extraction; hidden Markov models; neural nets; probability; signal classification; speech recognition; HMM; PNN; classification; emotional characteristics; feature matching sequence; hybrid model; identify significant limitations; recognition model; speech affective recognition; speech recognition; speech signals; Hidden Markov models; Neural networks; Neurons; Probabilistic logic; Speech recognition; Support vector machine classification; Training;
Conference_Titel :
Advanced Computational Intelligence (ICACI), 2012 IEEE Fifth International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4673-1743-6
DOI :
10.1109/ICACI.2012.6463370
