An identity authentication method for intelligent logging evaluation expert system based on voiceprint recognition

Abstract

The invention relates to an intelligent well logging evaluation expert system identity authentication method based on voiceprint recognition. The method comprises the following steps of: collecting voiceprint waveforms of an interpretation expert user on the same text pronunciation to form a voiceprint template library; obtaining an interpretation expert name requiring the identity authentication through the indication of a user to be recognized; collecting user pairs to be recognized and the voiceprint waveform of the voiceprint template library; extracting a voiceprint template corresponding to the interpretation expert name from the voiceprint template library; performing anti-interference preprocessing on the voiceprint templates of an interpretation expert and the user to be recognized, and extracting voiceprint features to form sample feature vector sequences; and calculating the matching distance between the sample feature vector sequence of the user to be recognized and the sample feature vector sequence of the interpretation expert, and judging the user to be recognized as the indicated interpretation expert. The method has the advantages that the authentication accuracy rate is high; the speed is high; the robustness is high; and too slow and too fast voice can be accurately recognized, and the like.

Description

technical field [0001] The invention relates to an identity authentication method for an intelligent logging evaluation expert system based on voiceprint recognition, belongs to the technical field of computer information security, and is applied to the field of logging processing and interpretation software. Background technique [0002] A variety of intelligent logging evaluation expert systems for petroleum logging interpretation have been developed abroad, such as Schlumberger's stratum dip interpretation consulting system and lithology pattern recognition (LITHO) expert system, and Shell Petroleum's petrophysical property evaluation knowledge base system (LOGIX). In China, there are mainly OWLI and LIX logging interpretation intelligent expert systems in Huabei Oilfield and Shengli Oilfield, but these intelligent logging evaluation expert systems lack user identity authentication and authority division, which may easily cause the expert knowledge base to be illegally mo...

AI Technical Summary

Problems solved by technology

Disadvantages: (1) The characteristics of the voiceprint information do not fully conform to the Gaussian distribution, which is not consistent with the Gaussian model; (2) The selection of the initial parameters of the model is relatively random, which seriously affects the recognition rate of the system; (3) Build a Gaussian mixture model and train the algorithm The complexity is high, and the covariance matrix elements are prone to be less than zero during the iterative process, resulting in the inability to train the final model

Disadvantages: (1) Searching the nearest codeword of the training vector from the codebook requires a large amount of storage space and cumbersome calculations. When using a large codebook and high-dimensional vector, the computational complexity will be very large; (2) the initial codebook The choice of affects the convergence speed of codebook training and the performance of the final codebook

[0007] In practical applications, it is also found that the robustness of these two methods is poor, and the recognition rate for the voiceprints to be recognized that are too slow and too fast is very low

Images