Voiceprint recognition method based on negative correlation incremental learning

Abstract

The invention provides a voiceprint recognition method based on negative correlation incremental learning. The method comprises: step one, preprocessing and feature extraction are carried out on an inputted voice signal; step two, network integration is initialized; and if network integration already exists, current all networks are copied; step three, the network integration is trained; step four, structure adjustment is carried out on each network in the network integration; step five, the current networks are screened and the part of optimal networks are selected; and step six, the currently obtained networks are applied; and if new data arrive, steps are executed circularly by starting with the step one. According to the voiceprint recognition method provided by the invention, with the incremental learning method, voiceprint recognition is studied, so that the efficiency and identification accuracy under the data incremental arrival scene can be improved; and an incremental problem can be solved by using the negative-correlation-learning-based incremental learning algorithm. Improvement is carried out from perspectives of model training and model selection and thus a novel algorithm is put forward to solve problems; and then the novel method is applied to incremental learning.

Description

technical field [0001] The invention relates to a voiceprint recognition method. Background technique [0002] Voiceprint refers to the sound wave information map that reflects the speaker's voice spectrum. Voiceprint recognition is a technology that automatically recognizes and judges the speaker's identity based on the speech parameters including the speaker's characteristics reflected in the speech waveform map. Due to the different vocal organs of each person, the characteristics and pitch of the sound they emit are also different. Therefore, using voiceprint as a personality feature to realize the identification and verification of different people has the characteristics of fast, stable and high accuracy. The technology of fingerprint recognition is also being widely used in various fields of information and network. [0003] However, in a large number of application scenarios, the training data cannot be obtained at one time, and voiceprint recognition also has some ...

AI Technical Summary

Problems solved by technology

SNCL has better generalization performance, but its time complexity is much higher than other algorithms. In addition, it is difficult to determine the number of hidden layer nodes of individual networks, which is prone to overfitting and other phenomena.

Images