Method and device for training speaker recognition model, electronic equipment and readable storage medium

A speaker recognition and speaker technology, which is applied in the field of training speaker recognition models, can solve the problems of low accuracy of speaker recognition models and inability to meet speaker recognition requirements, etc.

Pending Publication Date: 2021-09-14
SHANGHAI MININGLAMP ARTIFICIAL INTELLIGENCE GRP CO LTD
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy of the speaker recognition model trained on these corpora is...

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 and device for training speaker recognition model, electronic equipment and readable storage medium
  • Method and device for training speaker recognition model, electronic equipment and readable storage medium
  • Method and device for training speaker recognition model, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] In order to understand the characteristics and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. The attached drawings are only for reference and description, and are not intended to limit the embodiments of the present disclosure. In the following technical description, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawings.

[0016] The terms "first", "second" and the like in the description and claims of the embodiments of the present disclosure and the above drawings are used to distinguish similar objects, and are not necessarily 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
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to the technical field of speech recognition and discloses a method for training a speaker recognition model. The method comprises steps of obtaining a to-be-classified corpus; inputting the to-be-classified corpus into a preset classification model, and determining whether the to-be-classified corpus belongs to the vertical field or not; and under the condition that the to-be-classified corpus belongs to the vertical field, training a first speaker recognition model by using the to-be-classified corpus. According to the method, the obtained to-be-classified corpora are inputted into the classification model for classification, and the to-be-classified corpora belonging to the vertical field are utilized to train the speaker recognition model, so accuracy of the speaker recognition model related to the vertical field is improved, and speaker recognition requirements for the vertical field can be met. The invention further discloses a device for training the speaker recognition model, electronic equipment and a readable storage medium.

Description

technical field [0001] The present application relates to the technical field of speech recognition, for example, to a method, device, electronic device and readable storage medium for training a speaker recognition model. Background technique [0002] At present, with the popularization of intelligent customer service systems, smart home systems, intelligent teaching robots, etc., language models are more and more applied to all aspects of life. For example, the speaker recognition model in the language model is used to confirm whether the corpus data is the same person Said. However, in some special vertical fields such as banking and insurance, there are professional and unique expressions, and the differences between semantic expressions are small. The existing technology usually adopts a generative method to obtain vertical field-related corpus for training these language models, that is, preset several ordered semantic expressions according to the business goals relat...

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): G10L17/04
CPCG10L17/04
Inventor 江民
Owner SHANGHAI MININGLAMP ARTIFICIAL INTELLIGENCE GRP 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