Voice interaction method and system based on wav2vec mood word insertion

A technology of voice interaction and modal particles, applied in the field of speech recognition and artificial intelligence, can solve problems such as poor feedback of modal particles, high professionalism, and complicated rules, so as to improve generalization, avoid abruptness, and stability high effect

Active Publication Date: 2022-03-22
HANGZHOU YIWISE INTELLIGENT TECH CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of the existing customer service robots in human-computer voice interaction, the feedback effect of the robot during the user's speech is not good, or the rules are complicated and professional, the present invention proposes a wav2vec-based modal particle The inserted voice interaction method and system improve the user's dialogue experience in the process of man-machine voice interaction, and are easy to operate

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
  • Voice interaction method and system based on wav2vec mood word insertion
  • Voice interaction method and system based on wav2vec mood word insertion
  • Voice interaction method and system based on wav2vec mood word insertion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0030] The flowcharts shown in the figures are illustrative only and do not necessarily include all steps. For example, some steps can be decomposed, and some steps can be combined or partly combined, so the actual execution sequence may be changed according to the actual situation.

[0031] A kind of speech interaction method based on the modal part...

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 provides a wav2vec-based mood word insertion voice interaction method and system, and belongs to the technical field of artificial intelligence and voice recognition. The method comprises the following steps: training a wav2vec pre-training model in a Chinese speech environment; obtaining a user call audio and marking a mood word insertion position as an audio corpus; the method comprises the following steps: cutting an audio corpus, setting an insertion label or no insertion label for each cut voice block, and forming a training sample set by taking each voice block with a label as a sample; according to the method, the audio classification model composed of the wav2vec pre-training model and the classifier is constructed and trained, whether a mood word needs to be inserted in the man-machine voice interaction process is judged by using the trained audio classification model, the stability is high, the abrupt property of random insertion is avoided, complex rules do not need to be designed by professionals, and the accuracy is high.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence and voice recognition, in particular to a voice interaction method and system for inserting modal particles based on wav2vec. Background technique [0002] Artificial intelligence technology is becoming more and more mature. In many scenarios, robot customer service can replace manual customer service to communicate with users, reducing labor costs. However, in the prior art, human-computer voice interaction still has many deficiencies. For example, the dialogue mode of the existing customer service robot is blocking, that is, when the user is speaking, the robot will wait forever. If the user speaks a long series of sentences, the robot will remain silent and have no feedback, which greatly reduces the user's dialogue. experience. [0003] At present, some customer service robots randomly insert modal particles when the user speaks. The response effect of this kind of reply is ...

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): G06F16/632G06F16/65G06N3/08G06Q30/02
CPCG06F16/632G06F16/65G06N3/08G06Q30/0281
Inventor 李立峰姜兴华虞赵阳
Owner HANGZHOU YIWISE INTELLIGENT TECH 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