Voiceprint recognition method, device and apparatus for original voice, and storage medium

Abstract

The invention relates to the field of artificial intelligence, and discloses a voiceprint recognition method for original voice, which is used for reducing information loss and system complexity of anoriginal voice data recognition model of a speaker. The method comprises the steps of obtaining original voice data, and performing segmentation processing on the original voice data according to a preset time length to obtain segmented voice data; performing tail biting convolution processing and discrete Fourier transform processing on the segmented voice data through a preset convolution filter bank to obtain voiceprint feature data; pooling the voiceprint feature data through a preset deep neural network to obtain target voiceprint features; performing embedded vector conversion processing on the target voiceprint feature to obtain a corresponding voiceprint feature vector; and calculating the voiceprint feature vector through a preset loss function to obtain target voiceprint data, the loss function comprising a cosine similarity matrix loss function and a minimum mean square error matrix loss function. The invention also relates to a blockchain technology, and the voiceprint feature data is stored in the blockchain.

Description

technical field [0001] The invention relates to the field of speech signal processing, in particular to a voiceprint recognition method, device, equipment and storage medium for original speech. Background technique [0002] At present, the speaker's original speech data recognition model extracts the feature information from the speaker's original speech data through artificial feature engineering, generates vector data of the feature information, and performs channel noise fitting processing on the vector data to obtain the fitting processing data. Fitting and processing the data for speaker recognition and obtaining the corresponding speaker information. [0003] Since the obtained vector data cannot be directly used to identify the channel information difference between the same speaker or different speakers, it is necessary to perform channel noise fitting processing on the obtained vector data to obtain the fitting processing data, and then the The back-end reprocessi...

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to solve the problems of high information loss and high system complexity existing in the existing speaker original speech data recognition model

Images