scholarly journals An Emotion Recognition System based on Right Truncated Gaussian Mixture Model

2012 ◽  
Vol 42 (10) ◽  
pp. 41-45
Author(s):  
N. MuraliKrishna ◽  
Y. Srinivas ◽  
P. V. Lakshmi
Keyword(s):  
Emotion Recognition ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Truncated Gaussian

Speech Emotion Recognition under White Noise

2013 ◽  
Vol 38 (4) ◽  
pp. 457-463 ◽  
Author(s):  
Chengwei Huang ◽  
Guoming Chen ◽  
Hua Yu ◽  
Yongqiang Bao ◽  
Li Zhao
Keyword(s):  
White Noise ◽  
Emotion Recognition ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Speech Enhancement ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Class Model ◽  
Space Model ◽  
Dimension Space

Abstract Speaker‘s emotional states are recognized from speech signal with Additive white Gaussian noise (AWGN). The influence of white noise on a typical emotion recogniztion system is studied. The emotion classifier is implemented with Gaussian mixture model (GMM). A Chinese speech emotion database is used for training and testing, which includes nine emotion classes (e.g. happiness, sadness, anger, surprise, fear, anxiety, hesitation, confidence and neutral state). Two speech enhancement algorithms are introduced for improved emotion classification. In the experiments, the Gaussian mixture model is trained on the clean speech data, while tested under AWGN with various signal to noise ratios (SNRs). The emotion class model and the dimension space model are both adopted for the evaluation of the emotion recognition system. Regarding the emotion class model, the nine emotion classes are classified. Considering the dimension space model, the arousal dimension and the valence dimension are classified into positive regions or negative regions. The experimental results show that the speech enhancement algorithms constantly improve the performance of our emotion recognition system under various SNRs, and the positive emotions are more likely to be miss-classified as negative emotions under white noise environment.

scholarly journals A GAUSSIAN MIXTURE MODEL-BASED SPEAKER RECOGNITION SYSTEM

2017 ◽  
Vol 10 (13) ◽  
pp. 140
Author(s):  
Kumari Piu Gorai ◽  
Thomas Abraham
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Speaker Recognition ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Human Being ◽  
Biometric System ◽  
Voice Signal ◽  
Signal Characteristics ◽  
Authentication Technique

A human being has lot of unique features and one of them is voice. Speaker recognition is the use of a system to distinguish and identify a person from his/her vocal sound. A speaker recognition system (SRS) can be used as one of the authentication technique, in addition to the conventional authentication methods. This paper represents the overview of voice signal characteristics and speaker recognition techniques. It also discusses the advantages and problem of current SRS. The only biometric system that allows users to authenticate remotely is voice-based SRS, we are in the need of a robust SRS.

scholarly journals Comparison of Parametric representations of Birdcall in Gaussian Mixture model

2017 ◽  
Vol 2 (3) ◽  
pp. 124-130
Author(s):  
Ricky Mohanty ◽  
Sandeep Singh Solanki
Keyword(s):  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Bird Species ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Extraction Methods ◽  
Paper Briefly ◽  
Mel Frequency Cepstral Coefficients ◽  
Model Classification ◽  
Audio Recordings

This paper focuses on the methods of automatic classifications of birds into different species based on feature extraction methods & audio recordings of their sounds. The recognition system uses Gaussian mixture model (GMM) to model 14 poultry bird species calls. Mel frequency cepstral coefficients (MFCC) parameters & wavelet parameters are used for feature vector extraction. The paper briefly explains the methods &  also evaluates the performance of these methods in Gaussian Mixture Model classification .The results depicts the performance of  Gaussian Mixture Model classification using wavelet was more efficient in terms of percentage of accuracy  at around 80% and computation was also faster.

Sign in / Sign up

Export Citation Format

Share Document