Voiceprint recognition method based on variational information bottleneck and system thereof

Abstract

The invention provides a voiceprint recognition method based on variational information bottleneck and a system thereof, and solves the problems of poor robustness and low discrimination of speaker embedding extracted by an existing voiceprint recognition model. The method comprises the following steps: firstly, providing a feature extraction network consisting of VovNet and an ultra-lightweight subspace attention mechanism (ULSAM), wherein the feature extraction network is used for extracting multi-scale and multi-frequency frame-level speaker information; and then introducing a variational information bottleneck as a regularization method, further compressing the feature vector of the speaker, removing information irrelevant to the speaker, and only keeping information relevant to identification of the identity of the speaker, so that embedding of the finally extracted speaker is more robust. Compared with an existing voiceprint recognition technology, the voiceprint recognition method improves the recognition accuracy of voiceprint recognition under the noise background, and enables the voiceprint recognition technology to be more suitable for actual life scenes.

Description

technical field [0001] The invention relates to the fields of deep learning and voiceprint recognition, in particular to a voiceprint recognition method and system based on a variational information bottleneck. Background technique [0002] Voiceprint recognition, also known as speaker recognition, is a technology that automatically identifies the speaker's identity based on the speech parameters in the sound waveform that reflect the speaker's physiological and behavioral characteristics. The emergence of deep learning has greatly promoted the development of voiceprint recognition. End-to-end voiceprint recognition based on deep neural network has become the current mainstream technology, that is, to use the powerful learning ability of deep neural network to learn a language from voice signals. Person representation vectors, called speaker embeddings. [0003] Voiceprint recognition based on deep speaker embeddings usually consists of three parts: feature extraction netwo...

AI Technical Summary

Problems solved by technology

[0006] The present invention proposes a voiceprint recognition method and system based on a variational information bottleneck, which is used to solve or at least partially solve the technical problem of low voiceprint recognition accuracy in practical application scenarios

Images