Voiceprint recognition method based on gender, nationality and emotion information

Abstract

The invention discloses a voiceprint recognition method based on gender, nationality and emotion information. The method specifically comprises the following steps: firstly, data preprocessing, secondly, feature extraction, and secondly, neural network parameter training: according to the specific structure of a neural network, in the training process, the input sequence of training sentences is disrupted, then 128 sentences are randomly selected as a training batch, and the number of data iterations is 80; wherein a training file required by the scoring fusion tool is a development set resultand a test set result of each system; wherein VOXCELEB1 test is used in the test set; wherein the development set is a test file which is generated based on 1211 training speaker statements and comprises 40,000 test pairs; and a final test set scoring result is obtained through 100 times of iteration. According to the invention, the recognition rate is improved.

Description

technical field [0001] The invention relates to the field of text-independent speaker recognition, in particular to multi-task and confrontational domain adaptation training, specifically a voiceprint recognition method based on gender, nationality and emotional information. Background technique [0002] Speech contains different kinds of attributes, such as content, gender, nationality, emotion, age and so on. These attributes affect the accuracy of speaker recognition when performing speaker verification tasks. Subjectively speaking, gender and nationality information can provide multiple verifications for the identity of the speaker to increase the recognition rate. However, when the emotions contained in different sentences of the same speaker are inconsistent, it will seriously affect the extraction of the speaker's personalized features. Thereby reducing the system recognition rate. [0003] Existing methods improve system performance from three aspects: 1) increase ...

AI Technical Summary

Problems solved by technology

These attributes affect the accuracy of speaker recognition when performing speaker verification tasks

Subjectively speaking, gender and nationality information can provide multiple verifications for the identity of the speaker to increase the recognition rate. However, when the emotions contained in different sentences of the same speaker are inconsistent, it will seriously affect the extraction of the speaker's personalized features. Thereby reducing the system recognition rate

[0003] Existing methods improve system performance from three aspects: 1) increase the amount of training data; 2) increase the depth or complexity of the network; 3) design a more ingenious loss function; however, due to the limited learning ability of the neural network, in order to To further improve the performance of the system without increasing the training complexity, it is essential to add more constraints during the training phase

Images