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

Method and device for determining interaction text in speech input

A voice input and text technology, applied in the field of data processing, can solve problems such as inconsistent user input intentions, terminal inability to control business positioning, etc., and achieve the effect of improving experience

Active Publication Date: 2017-10-27
HISENSE
View PDF6 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0016] In order to solve the problem that in practical applications, affected by factors such as the noise of the user's environment and the user's spoken language, the recognition result used to determine the interactive text in voice input is often inconsistent with the user's input intention, the embodiment of the present invention provides Provided is a method and device for determining interactive text in voice input, which can effectively prevent the recognition result used for determining interactive text in voice input from not existing in the text library of the terminal, and prevent the terminal from being unable to perform control services based on the recognized text position

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
  • Method and device for determining interaction text in speech input
  • Method and device for determining interaction text in speech input
  • Method and device for determining interaction text in speech input

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Compared with the traditional text input method, the voice input method is more in line with people's daily habits, making the user's input process more efficient. However, affected by factors such as the noise of the user's environment and the user's spoken dialect, there are obvious errors in the recognition results of speech recognition, or the recognition results with obvious errors are often inconsistent with the user's input intention.

[0041] Please refer to figure 1 , which shows a flow chart of a method for determining interactive text in speech input provided by an embodiment of the present invention. The method for determining interactive text in voice input may include the following steps:

[0042] Step 101, recognize the voice data input by the user, and obtain the recognized text of the voice data.

[0043] Optionally, use a large amount of speech data and the speech text corresponding to the speech data to train the acoustic model (such as the GMM-HMM mo...

Embodiment 2

[0066] When there are errors in the recognition text itself (for example: some words in the text are wrong, words are missing in the text, multiple words are added in the text, and the order of words in the text is reversed), the terminal can use the method of text-based similarity retrieval Retrieve the preset text corresponding to the recognized text, so that the retrieved preset text includes as much as possible the correct text that the user intended to input, and improve the correct rate of determining the interactive text in the voice input.

[0067] Please refer to figure 2 , which shows a flow chart of a method for determining interactive text in voice input provided by another embodiment of the present invention. The method for determining interactive text in voice input may include the following steps:

[0068] Step 201, recognize the voice data input by the user, and obtain the recognized text of the voice data.

[0069] Step 202, if at least one word segment inc...

Embodiment 3

[0086] When the text obtained by the terminal after speech recognition has the same pronunciation as the text input by the user and the text characters are different, resulting in a deviation in the text recognized by the terminal, the terminal can use the method of similarity retrieval based on pronunciation elements to retrieve the preset corresponding to the recognized text Text, so that the retrieved preset text contains as much as possible the correct text that the user intends to input, and improves the accuracy of determining the interactive text in voice input.

[0087] Please refer to image 3 , which shows a flow chart of a method for determining interactive text in speech input provided by another embodiment of the present invention. The method for determining interactive text in voice input may include the following steps:

[0088] Step 301, recognize the voice data input by the user, and obtain the recognized text of the voice data.

[0089] Step 302, if at leas...

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 method and device for determining an interaction text in speech input and belongs to the data processing field. The method comprises the following steps: identifying speech data input by a user to obtain an identification text of the speech data; if the identification text cannot be matched with a preset text library, obtaining at least one preset text, the text similarity between which and the identification text is larger than a first preset threshold value, in the text library; calculating pronunciation similarity between a pronunciation element string of the preset text and a pronunciation element string of the identification text; and determining the preset text, the pronunciation similarity is maximum, in the preset texts as the interaction text of the speech data. Therefore, the problem that, in practical application, the identification result of determination of the interaction text in the speech data is always inconsistent with user's input intents is solved; and the case that since the identification result of determination of the interaction text in the speech data does not exist in the text library of a terminal, the terminal cannot carry out control service positioning according to the identification text is avoided.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a method and device for determining interactive text in speech input. Background technique [0002] With the rapid development of science and technology in recent years, the control technology for determining interactive text in voice input has been gradually applied to various terminal devices. The user can perform voice control on the terminal device through the device configured on the terminal device for determining the interactive text in voice input, which brings new changes to the control technology of the terminal device. Currently, voice control has become a mainstream control method for terminal equipment. [0003] Take the TV as an example. Generally, the TV is equipped with a voice application program, such as a voice assistant. The user performs voice input through the voice assistant, and the TV recognizes the user's voice input to obtain text, and then the TV genera...

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
IPC IPC(8): G10L15/26G06F17/30
CPCG06F16/3343G10L15/26
Inventor 胡伟凤高雪松
Owner HISENSE
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com