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

Voice interaction method and device

A voice interaction and voice technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as deficiencies, inaccurate judgment results, and reduced user experience effects, so as to reduce the number of times, improve accuracy, and improve user experience. Effect

Active Publication Date: 2019-02-22
IFLYTEK CO LTD
View PDF11 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the development and maturity of intelligent voice interaction technology, the understanding and response of robots to semantics are becoming more and more humane. However, there are still deficiencies in the ability to adapt to the expression rhythm of different users.
[0003] Although the existing voice interaction methods can simulate alternate dialogues with real people to a certain extent, each user has their own different expression habits. Therefore, if a unified rule is used to judge whether a piece of voice is over, the judgment result will be inaccurate phenomenon, which affects the accuracy of subsequent semantic understanding and voice response, and reduces the effect of 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
  • Voice interaction method and device
  • Voice interaction method and device
  • Voice interaction method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0086] see figure 1 , which is a schematic flowchart of a voice interaction method provided in this embodiment, the method includes the following steps:

[0087] S101: During the current round of voice interaction, determine the user voice of the current user in the current round of interaction according to the current inter-sentence pause threshold.

[0088] In this embodiment, the system (such as a robot) may have one or more rounds of voice interaction with the current user. For example, the robot may be the first voice interaction with the current user, or it may be two , three times, etc., for multiple voice interactions. In addition, during each round of voice interaction, the silence detection technology may be used to determine the user's voice in each round of voice interaction according to the inter-sentence pause threshold corresponding to each round. It should be noted that this embodiment does not limit the language of the user's voice. For example, the user's v...

no. 2 example

[0136] This embodiment will introduce the specific implementation process of "responding to the current round of user voice" in the first step S102.

[0137] It should be noted that in the process of voice interaction, users often add some modal particles and catchphrases, such as "ah", "ah", "this", "that", etc., when expressing the user's voice. As an invalid expression, meaningless words are not conducive to the semantic understanding of the user's voice, but may also cause certain interference, especially when these words are located in the middle of valid words, which will affect the normal semantic understanding of the user's voice. Moreover, different users may generate some personalized modal particles, catchphrases and other meaningless words according to their own different expression habits when performing user voice expression. Therefore, after determining the actual inter-sentence pauses and each sentence-end pause in the current round of user speech, one way is t...

no. 3 example

[0156] This embodiment will introduce a voice interaction device, and for related content, please refer to the foregoing method embodiments.

[0157] see Figure 11 , which is a schematic composition diagram of a voice interaction device provided in this embodiment, the device 1100 includes:

[0158] The user voice determining unit 1101 is configured to determine the user voice of the current user in the current round of interaction according to the current inter-sentence pause threshold during the current round of voice interaction;

[0159] A pause threshold determining unit 1102, configured to determine a new pause threshold between sentences according to the user voice, and update the current pause threshold between sentences using the new pause threshold between sentences;

[0160] The user voice response unit 1103 is configured to respond to the user voice.

[0161] In an implementation of this embodiment, the pause threshold determining unit 1102 includes:

[0162] A...

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 voice interaction method and a voice interaction device. The voice interaction method comprises the steps of: determining, according to a current inter-sentence pause threshold value, user voice of a current user in a current round of interaction during the current round of voice interaction process; determining a new inter-sentence pause threshold value according to theuser voice; and utilizing the new inter-sentence pause threshold value to update the current inter-sentence pause threshold value, and responding to the user voice in the current round. Therefore, theinter-sentence pause threshold values alternately used in each round can be dynamically adjusted, so as to adapt to the pause habits of the user dynamically, thereby being capable of improving the accuracy of the voice response result, reducing the number of times that the user repeats the same problem, and further enhancing the user experience.

Description

technical field [0001] The present application relates to the technical field of voice recognition, in particular to a voice interaction method and device. Background technique [0002] With the development and maturity of intelligent voice interaction technology, the robot's understanding and response to semantics are becoming more and more humane. However, there are still deficiencies in the ability to adapt to the expression rhythm of different users. [0003] Although the existing voice interaction methods can simulate the alternate conversations of real people to a certain extent, each user has their own different expression habits. Therefore, if a unified rule is used to judge whether a piece of voice is over, the judgment result will be inaccurate phenomenon, which affects the accuracy of subsequent semantic understanding and voice response, and reduces the effect of user experience. Contents of the invention [0004] The main purpose of the embodiments of the pres...

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): G10L15/22G10L15/04
CPCG10L15/04G10L15/22
Inventor 马雪涛薛臣臣熊勇军
Owner IFLYTEK CO LTD