Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Training sample selection method and device for speech recognition model, and medium

A speech recognition model and training sample technology, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as inability to correctly identify input, pronunciation errors, etc., to improve accuracy and practicability, improve fault tolerance, and achieve pronunciation fault tolerance processing effect

Pending Publication Date: 2020-09-25
BEIJING AIYISHENG TECH CO LTD
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above problems, the object of the present invention is to provide a training sample selection method, device and medium for a speech recognition model, to solve the problem that the speech recognition model in the current intelligent speech input method cannot correctly recognize the input text due to incorrect pronunciation

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
  • Training sample selection method and device for speech recognition model, and medium
  • Training sample selection method and device for speech recognition model, and medium
  • Training sample selection method and device for speech recognition model, and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art would recognize that the described embodiments can be modified in various ways or combinations thereof without departing from the spirit and scope of the invention. Accordingly, the drawings and description are illustrative in nature and not intended to limit the scope of the claims. Also, in this specification, the drawings are not drawn to scale, and like reference numerals denote like parts.

[0030] figure 1 It is a schematic flow chart of the training sample selection method of the speech recognition model of the present invention, as figure 1 As shown, the training sample selection method of the speech recognition model of the present invention includes:

[0031] Step S1, obtaining the correct pronunciation training samples of the speech to be recognized, wherein the correct pronunciation training samples are the training samples de...

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 training sample selection method and device for a speech recognition model, and a medium, and the method comprises the steps: obtaining a correct pronunciation training sample of to-be-recognized speech; performing similar character expansion on the Chinese characters in the to-be-recognized speech; constructing and forming a fault-tolerant training sample by utilizing the expanded similar characters; and fusing the correct pronunciation training sample and the fault-tolerant training sample into a model training sample for training a speech recognition model. According to the method, pronunciation fault-tolerant processing is carried out on the training sample, so that the fault tolerance of a speech recognition system is improved, the purpose that correct candidate words can be provided by an input method even under the condition of pronunciation errors is achieved, and the accuracy and practicability of speech input are improved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device and medium for selecting training samples of a speech recognition model. Background technique [0002] With the rapid development of speech recognition technology, intelligent voice input method is gradually becoming a common choice for text entry, and is increasingly used in many scenarios in different industries. The intelligent speech input method takes speech recognition technology as the core, and mainly includes feature extraction, acoustic model, language model, dictionary and decoding. By extracting the acoustic features of the speech data to be recognized, it is decoded into a phoneme array based on the acoustic model. Using the dictionary Corresponds to the text output by the language model. This strategy is based and premised on the correct pronunciation of Chinese characters. If the pronunciation is wrong, it is difficult to o...

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): G10L15/06G10L15/08G10L15/26
CPCG10L15/063G10L15/08G10L2015/0633G10L2015/088
Inventor 陶焜
Owner BEIJING AIYISHENG TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products