Speech Emotion Recognition Using Hybrid Generative and Discriminative Models
نویسندگان
چکیده
In this paper, we use Sequential Forward Selection to select 8 dimensional frame-level features from the total 69 dimensional features, and we reduce the dimensions of utterance-level eigenvectors from 63 to 12 by fisher discriminant. Then, two kinds of GMM multidimensional likelihoods are proposed for hybrid generative and discriminative models. Experimental results on Berlin emotional speech databases show that the GMM-MAP/SVM series hybrid model is the optimal Hybrid Generative and Discriminative Models, with the recognition rate up to 85.1%. Streszczenie. W artykule zaprezentowano system wykrywania emocji w głosie na podstawie modelu dyskryminacyjnego. Zaprezentowano badania skuteczności system na przykładzie bazy danych Berlin. (System wykrywania emocji w głosie na podstawie modelu dyskryminacyjnego)
منابع مشابه
Improving of Feature Selection in Speech Emotion Recognition Based-on Hybrid Evolutionary Algorithms
One of the important issues in speech emotion recognizing is selecting of appropriate feature sets in order to improve the detection rate and classification accuracy. In last studies researchers tried to select the appropriate features for classification by using the selecting and reducing the space of features methods, such as the Fisher and PCA. In this research, a hybrid evolutionary algorit...
متن کاملVoice-based Age and Gender Recognition using Training Generative Sparse Model
Abstract: Gender recognition and age detection are important problems in telephone speech processing to investigate the identity of an individual using voice characteristics. In this paper a new gender and age recognition system is introduced based on generative incoherent models learned using sparse non-negative matrix factorization and atom correction post-processing method. Similar to genera...
متن کاملA Hybrid MaxEnt/HMM ba
The aim of this work is to develop a practical framework, which extends the classical Hidden Markov Models (HMM) for continuous speech recognition based on the Maximum Entropy (MaxEnt) principle. The MaxEnt models can estimate the posterior probabilities directly as with Hybrid NN/HMM connectionist speech recognition systems. In particular, a new acoustic modelling based on discriminative MaxEn...
متن کاملDeep Discriminative and Generative Models for Pattern Recognition
In this chapter we describe deep generative and discriminative models as they have been applied to speech recognition and related pattern recognition problems. The former models describe the distribution of data or the joint distribution of data and the corresponding targets, whereas the latter models describe the distribution of targets conditioned on data. Both models are characterized as bei...
متن کامل