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

Semantic recognition method and device for voice data, storage medium and computer equipment

A technology of speech data and semantic recognition, applied in speech recognition, calculation, speech analysis, etc., can solve problems such as semantic understanding deviation, achieve the effect of avoiding secondary errors, saving steps, and improving accuracy

Inactive Publication Date: 2019-06-11
SHANGHAI XIAOI ROBOT TECH CO LTD
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the existing semantic understanding methods based on voice interaction and the output results of the system to voice data, there is still a problem of semantic understanding deviation

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
  • Semantic recognition method and device for voice data, storage medium and computer equipment
  • Semantic recognition method and device for voice data, storage medium and computer equipment
  • Semantic recognition method and device for voice data, storage medium and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] As mentioned in the background art, in the existing semantic understanding method based on voice interaction and the output result of the system for voice data, there is still a problem of semantic understanding deviation.

[0036] Based on the observation and research of the existing semantic understanding methods and systems based on voice interaction, the inventors of the present application found that, in addition to the deviation of the semantic understanding process itself, most of the deviations in semantic understanding mainly come from the following two aspects: 1. The pronunciation of the voice itself Features, for example, similar phonemes such as flat tongue and reflex tongue, resulting in the inability to obtain the correct phonetic text in the speech recognition process; second, there are a large number of phonetic features such as polyphonic characters, homophones, and near-phonetic characters in the language, resulting in the phonetic text During the conv...

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 semantic recognition method and device for voice data, a storage medium and computer equipment, and the method comprises the steps: converting the obtained voice data into aphonetic text, the phonetic text comprising at least one word voice identifier; preferentially using the near-tone word voice identifier with the maximum weight value to be matched with the word voiceidentifier in the preset dictionary; and under the condition that the near-phonetic word speech identifier with the maximum weight value is not matched with the word speech identifier in a preset dictionary, matching the near-phonetic word speech identifiers with other weights in the near-phonetic word class with the word speech identifiers in the preset dictionary to obtain a text, and performing semantic understanding processing on the text to obtain meanings of the voice data. Through the technical scheme of the invention, the speech recognition accuracy can be improved. According to the embodiment of the invention, the matching efficiency can be improved by adopting the matching mode.

Description

technical field [0001] The invention relates to the technical field of speech recognition, in particular to a method and device for semantic recognition of speech data, a storage medium, and computer equipment. Background technique [0002] With the development of speech recognition technology, speech recognition has been applied in many fields. Usually, the semantic understanding method and system based on voice interaction outputs a response to the input voice so that the user can perform further operations. [0003] In the prior art, the speech recognition processing process and the semantic understanding processing process are serial and independent of each other. Speech recognition is responsible for using speech recognition technology to recognize interactive speech into text, and semantic understanding is responsible for using semantic understanding technology to give semantic understanding responses based on speech recognition text. Specifically, in the speech reco...

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): G06F17/27G10L15/26
Inventor 韩潼瑜朱频频
Owner SHANGHAI XIAOI ROBOT 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