Unlock instant, AI-driven research and patent intelligence for your innovation.

Multi-dialect identification method, apparatus, device and readable storage medium

A recognition method, multi-dialect technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as poor user experience, low efficiency, and reduced accuracy of recognition, to simplify user operations, improve accuracy and efficiency. Effect

Active Publication Date: 2022-08-05
IFLYTEK CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing speech recognition solutions usually only support the recognition of Mandarin, and if the user uses a dialect, the recognition accuracy will be seriously reduced
Or although dialect recognition is supported, the user needs to manually select the recognition mode corresponding to the dialect, which requires the user's active cooperation. If the user's Mandarin and dialect are mixed, it is difficult to realize the initiative to switch modes, and in the scene of multi-person conversation , if there are speakers of multiple dialects, frequent switching will obviously lead to inefficiency and poor user experience

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
  • Multi-dialect identification method, apparatus, device and readable storage medium
  • Multi-dialect identification method, apparatus, device and readable storage medium
  • Multi-dialect identification method, apparatus, device and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0066] The inventor's research found that the existing speech recognition scheme uses an independent dialect recognition model when performing dialect recognition. For example, to recognize the voice of the first dialect, the For speech, you need to use the second dialect recognition model. The first dialect and the second dialect are different dialects. The first dialect recognition model is obtained by training the training corpus of th...

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 embodiment of the present application discloses a multi-dialect recognition method, device, device and readable storage medium. Dialect recognition is performed through a pre-built dialect recognition model, wherein the dialect recognition model is obtained by training a training corpus including multiple dialects. , and the training process of the dialect recognition model is not only limited to the speech content of the corpus, but also introduces the dialect type to which the dialect belongs, and optimizes the dialect recognition model in combination with the dialect type to which the dialect belongs, so that the dialect recognition model can accurately identify multiple dialects , so that the user does not need to switch the speech recognition mode, simplifies the user operation, and improves the accuracy and efficiency of multi-dialect recognition.

Description

technical field [0001] The present application relates to the technical field of speech recognition, and more particularly, to a multi-dialect recognition method, apparatus, device, and readable storage medium. Background technique [0002] At present, more and more artificial intelligence applications rely on speech recognition, such as translators that realize barrier-free communication between people in different languages ​​and different countries, robot customer service that greatly reduces human resources, voice input methods that free hands, For smart homes (home appliances) that are more convenient and natural to control home appliances, their entrances all rely on voice recognition, so the accuracy of voice recognition is particularly important. [0003] However, the existing speech recognition solutions usually only support the recognition of Mandarin, and if the user uses a dialect, the accuracy of the recognition will be seriously reduced. Or although dialect re...

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 Patents(China)
IPC IPC(8): G10L15/00G10L15/06G10L15/08
CPCG10L15/005G10L15/063G10L15/08
Inventor 许丽潘嘉
Owner IFLYTEK CO LTD