Paraphrase generation is a text data argumentation method based on Natural Language Generation （NLG）. Concerning the problems of repetitive generation， semantic errors and poor diversity in paraphrase generation methods based on the Sequence-to-Sequence （Seq2Seq） framework， a Paraphrase Generation Network based on Joint learning of Sequence and Graph （J-SGPGN） was proposed. Graph encoding and sequence encoding were fused in the encoder of J-SGPGN for feature enhancement， and two decoding methods including sequence generation and graph generation were designed in the decoder of J-SGPGN for parallel decoding. Then the joint learning method was used to train the model， aiming to combine syntactic supervision with semantic supervision to simultaneously improve the accuracy and diversity of generation. Experimental results on Quora dataset show that the generation accuracy evaluation indicator METEOR （Metric for Evaluation of Translation with Explicit ORdering） of J-SGPGN is 3.44 percentage points higher than that of the baseline model with optimal accuracy — RNN+GCN， and the generation diversity evaluation indicator Self-BLEU （Self-BiLingual Evaluation Understudy） of J-SGPGN is 12.79 percentage points lower than that of the baseline model with optimal diversity — Back-Translation guided multi-round Paraphrase Generation （BTmPG） model. It is verified that J-SGPGN can generate paraphrase text with more accurate semantics and more diverse expressions.

Concerning the low identification precision of Mel Frequency Cepstral Coefficients (MFCC) parameters in high frequency signals and the problem that the influence of each dimension feature parameters has not been considered to identify, the method of extracting features based on MFCC, IMFCC (Inverted MFCC) and MidMFCC (Mid-frequency MFCC) combined with Fisher criterion was adopted. Extracting MFCC, IMFCC and MidMFCC parameters from speech signals and calculating the Fisher ratio of components of three parameters, useful parameters were chosen by using Fisher standard and a mixture feature was constructed to improve mid-frequency and high frequency recognition accuracy. The experimental results show that the new feature has better recognition results compared with MFCC in the same environment.