Method for updating voiceprint feature model and terminal

A voiceprint feature and model update technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of inability to guarantee, the voiceprint feature model cannot improve the recognition accuracy, etc., to improve accuracy, improve accuracy and recognition. The effect of accuracy

Inactive Publication Date: 2012-10-31
HUAWEI DEVICE CO LTD
View PDF7 Cites 105 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present invention is to provide a voiceprint feature model update method and terminal, aiming at solving the problem that the accuracy of the voiceprint feature model cannot be improved under the premise of high practicability when the existing method is used to obtain the voiceprint feature model. degree, resulting in the problem that the recognition accuracy cannot be improved by using the voiceprint feature model

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
  • Method for updating voiceprint feature model and terminal
  • Method for updating voiceprint feature model and terminal
  • Method for updating voiceprint feature model and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 The implementation flow of the method for updating the voiceprint feature model provided by the first embodiment of the present invention is shown, and the details are as follows:

[0028] In step S101, an original audio stream containing at least one speaker is obtained.

[0029] Wherein, the original audio stream may be an audio stream generated by the user through a mobile terminal to make a phone call, voice chat, etc., or may be an audio stream obtained by means of recording or the like. Specifically, when a mobile terminal user is connected to the phone, the user is prompted whether to agree to use the voiceprint learning function. After the user agrees, the audio stream generated during the speaking process is recorded; The switch to enable the voiceprint learning function during a call can be set by the user as needed; or the terminal is equipped with the voiceprint learning function, and the user can record the audio stream by himself. It should be n...

Embodiment 2

[0039] figure 2 The implementation flow of the method for updating the voiceprint feature model provided by the second embodiment of the present invention is shown, and the details are as follows:

[0040] In step S201, an original voiceprint feature model is established according to preset audio stream training samples.

[0041] Wherein, the original voiceprint feature model is a voiceprint feature model established according to preset audio stream training samples by calling the voiceprint registration algorithm interface, and the original voiceprint feature model is a voiceprint registration completed for a certain person or multiple people The feature model formed after the registration process does not require the length of the training corpus or audio stream training samples. And because the method provided by the embodiment of the present invention can realize continuous dynamic correction of the corrected model, etc., the original voiceprint feature model can be a mo...

Embodiment 3

[0063] Figure 4 It shows the structure of the terminal provided by the third embodiment of the present invention. The terminal provided by the third embodiment of the present invention can be used to implement the methods realized by the first to second embodiments of the present invention. For relevant parts and specific technical details not disclosed, please refer to Embodiment 1 and Embodiment 2 of the present invention.

[0064] The terminal can be terminal equipment including mobile phone, tablet computer, PDA (Personal Digital Assistant, personal digital assistant), POS (Point of Sales, sales terminal), vehicle-mounted computer, etc. Figure 4 Shown is a block diagram of a partial structure of the mobile phone 400 related to the terminal provided by the embodiment of the present invention. refer to Figure 4 , the mobile phone 400 includes an RF (Radio Frequency, radio frequency) circuit 410, a memory 420, an input unit 430, a display unit 440, a sensor 450, an audio...

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 is suitable for the technical field of voice recognition and provides a method for updating a voiceprint feature model. The method comprises the following steps of: obtaining an original audio stream of at least one speaker, and obtaining the audio stream of each speaker in the at least one speaker in the original audio stream according to a preset speaker segmentation and clustering algorithm; matching the respective audio stream of each speaker in the at least one speaker with an original voiceprint feature model, so as to obtain the successfully-matched audio stream; and using the successfully-matched audio stream as an additional audio stream training sample used for generating the original voiceprint feature model, and updating the original voiceprint feature model. According to the invention, the valid audio stream during a conversation process is adaptively extracted and used as the additional audio stream training sample, and the additional audio stream training sample is used for dynamically correcting the original voiceprint feature model, thus achieving a purpose of improving the precision of the voiceprint feature model and the accuracy of recognition under the premise of high practicability.

Description

technical field [0001] The invention belongs to the technical field of speech recognition, and in particular relates to a method for updating a voiceprint feature model and a terminal. Background technique [0002] Voiceprint recognition is a recognition technology that utilizes human voice. Since there are certain differences in the vocal organs used by people when speaking, the voiceprint maps of any two voices are different, so voiceprints can be used to represent individual differences. The biological characteristics of different individuals can be represented by establishing a voiceprint feature model, and then the voiceprint feature model can be used to identify different individuals. At present, there is a dilemma in the application of the voiceprint feature model, which is mainly reflected in the selection of the length of the training corpus. Generally speaking, the longer the voiceprint training corpus, the more accurate the feature model and the higher the recogni...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/02
CPCG10L17/04G10L15/07G10L17/02G10L15/142G10L15/02G10L15/063G10L2015/0631
Inventor 卢霆
Owner HUAWEI DEVICE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap