Voiceprint recognition method based on multi-person speaking

A technology for voiceprint recognition and feature recognition, which is applied in the field of biometrics, and can solve the problems of limiting the application of voiceprint recognition algorithms, the inability to distinguish the speaker's voice, and the high complexity of voiceprint recognition, so as to achieve a small amount of calculation and save storage and calculation resources, the effect of improving accuracy

Inactive Publication Date: 2017-07-21
YUTOU TECH HANGZHOU
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above-mentioned process has the following problems: (1) the above-mentioned voiceprint recognition model needs to learn more samples before it can be applied; (2) the calculation complexity of the voiceprint recognition based on the above-mentioned recognition model is relatively high; (3) The amount of model data calculated based on the above-mentioned recognition model is large; (4) When multiple speakers speak at the same time, the voice of the speaker to be recognized cannot be distinguished
In summary, for intelligent systems with limited resources, the above-mentioned existing problems limit the application of voiceprint recognition algorithms in the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voiceprint recognition method based on multi-person speaking
  • Voiceprint recognition method based on multi-person speaking
  • Voiceprint recognition method based on multi-person speaking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0048] It should be noted that, in the case of no conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other.

[0049] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but not as a limitation of the present invention.

[0050] In a preferred embodiment of the present invention, based on the above-mentioned problems in the prior art,...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a voiceprint recognition method based on multi-person speaking, and belongs to the technical field of biological recognition. According to the voiceprint recognition method, when multiple persons speak at the same time, an acoustic source can be decomposed, voice of each speaker is obtained, voice of each speaker is matched with a preset frequency band, voice of a speaker needing to be recognized is recognized according to matching similarity, then voiceprint recognition is performed on the voice, the calculation amount is relatively small, storage and calculation resources can be saved, and the accuracy rate of recognition is high, problems existing in a modeling method based on probability statistics are overcome, and the voiceprint recognition method is suitable for an intelligent system with limited system resources to use. At the same time, a first frequency representing a child speaker and a second frequency representing an adult speaker are set in advance and are compared separately, thereby further improving the degree of accuracy of voiceprint recognition based on multi-person speaking.

Description

technical field [0001] The invention relates to the technical field of biological identification, in particular to a voiceprint identification method based on multiple people speaking. Background technique [0002] Voiceprint recognition, like fingerprints, iris, face recognition, etc., is a type of biometrics and is considered to be the most natural way of biometric identification. Relying on voiceprint recognition can easily verify the identity of the speaker, and the privacy of this verification method is very high, because voiceprint usually cannot be maliciously copied and stolen, so voiceprint recognition is especially useful in various fields. The field of equipment has outstanding application advantages. [0003] The basic process of voiceprint recognition is voice collection, feature extraction, and classification model. The common speech feature extraction method is to use the short-term stationary characteristics of the speech, and use the cepstrum transform met...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G10L17/08G10L17/14
CPCG10L17/08G10L17/14
Inventor祝铭明
OwnerYUTOU TECH HANGZHOU