The study includes the following four aspects: the phonetic and semantic features;the historical source;the distribution in the Modern Chinese Dialect;the change process and the development tendency.

The separability and application of pitch parameters in speaker recognition;

Having discussed various audio features and their extracting methods,we bring forward a new method for audio scene segmentation,according to the features of six kinds of audio signal types(silence,music,environmental sound,pure speech,speech with music and speech with environmental sound)to segment audio stream.

Based on using prosody features related to the arousal dimension of emotion, some voice quality features related to the valence dimension of emotion are proposed to be extracted as new emotional features for improving emotion recognition correct rate.

Based on extracting prosody and voice quality features from emotional speech, three kinds of classifiers including Support Vector Machines(SVM), K-Nearest Neighborhood(KNN) and Artificial Neural Network(ANN) are utilized to vote and construct an ensemble classifier so as to realize recognizing the four main speech emotion in Chinese like anger, happiness, sa.

Based on extracting fundamental prosody features from emotional speech,speech voice quality features are extracted to improve emotion recognition accuracies.