Voice instruction management method and system thereof

A voice command and command technology, applied in voice analysis, transmission system, voice recognition, etc., can solve problems such as misoperation and user distress

Inactive Publication Date: 2017-06-20
SHENZHEN TINNO WIRELESS TECH
5 Cites 3 Cited by

AI-Extracted Technical Summary

Problems solved by technology

In this way, there will often be false actions due to background voice noise (such as TV,...
View more

Abstract

The invention discloses a voice instruction management method and a system thereof. The method is characterized by comprising the following steps: a voice instruction is received through a voice receiving module, and through a voice feature similarity judgment module, whether the voice instruction is consistent with a feature parameter of a pre-inputted voice sample is compared; if yes, through a voice identification module, the voice instruction and a pre-inputted instruction sample are compared, and a target instruction corresponding to the voice instruction is judged; and through an instruction execution module, the target instruction corresponding to the voice instruction is executed.

Application Domain

Speech recognitionTransmission

Technology Topic

Speech soundFeature parameter

Image

  • Voice instruction management method and system thereof
  • Voice instruction management method and system thereof
  • Voice instruction management method and system thereof

Examples

  • Experimental program(1)

Example Embodiment

[0021] In order to further explain the technical means and effects of the present invention to achieve the intended purpose of the invention, the following is a detailed description of the specific implementation, structure, and structure of the voice command management control method and equipment proposed in the present invention with reference to the accompanying drawings and preferred embodiments. The characteristics and effects are described in detail later.
[0022] Specific embodiments of the present invention will be described in detail below with reference to the drawings.
[0023] Please refer to figure 1 , Is a schematic diagram of the system architecture of the voice command management of the present invention. figure 1 , The voice command management system 1 includes:
[0024] A voice receiving module 110 for receiving a voice command;
[0025] A voice feature similarity judgment module 120, which compares whether the voice command matches a feature parameter of a pre-input voice sample;
[0026] A voice recognition module 130 that compares the voice command with a pre-input command sample, and determines a command corresponding to the voice command; and
[0027] An instruction execution module 140 executes the target instruction corresponding to the voice instruction.
[0028] In this embodiment, it further includes: the voice feature similarity judgment module 120, which compares the voice command with the feature parameters of the pre-input voice sample, and when the result is found to be inconsistent, passes a prompt module , Prompting that the voice instruction does not match the characteristic parameter of the pre-input voice sample.
[0029] In this embodiment, it further includes: the voice recognition module 130, which compares the voice command with the pre-input command sample and fails to determine the command corresponding to the voice command through a voice assistant module, Conduct question and answer guidance.
[0030] In this embodiment, it further includes: the voice receiving module 110, which is connected to the voice feature similarity judgment module 120 by means of wireless transmission.
[0031] In this embodiment, it further includes: the voice receiving module 110 is a Bluetooth headset, a smart watch, a smart glasses, or a wearable device with a voice receiving function.
[0032] Please refer to figure 2 , Is a schematic diagram of the process of the voice command management method of the present invention.
[0033] Step S210: Receive a voice command through a voice receiving module.
[0034] Step S220: Through a voice feature similarity judgment module, compare whether the voice command matches a feature parameter of a pre-input voice sample.
[0035] Step S230: When it is determined that the voice command is consistent with a characteristic parameter of the pre-input voice sample, a voice recognition module is used to compare the voice command with a pre-input command sample to determine the corresponding voice command Of a target instruction.
[0036] In this embodiment, the voice recognition module uses a voice recognition to determine the effect of a command corresponding to the voice command
[0037] In this embodiment, the main purpose of the speech recognition is that the computer understands the voice of human beings, and then commands the computer to perform corresponding tasks. When the sound is input into the computer through the analog-to-digital conversion device and stored in a numerical manner, the voice recognition program starts to compare the stored sound samples with the input test sound samples. After the comparison is complete, you can know what the user's voice just meant, and then command the computer to do something.
[0038] The speech recognition used in this embodiment can have the following methods:
[0039] 1. According to the number of recognizable vocabulary: small vocabulary (hundreds of words), medium vocabulary (thousands of words), large vocabulary (tens of thousands of words).
[0040] 2. According to the use object: specific object (Speaker Dependent), unspecific object (SpeakerIndependent).
[0041] 3. According to the usage mode: discontinuous speech recognition, continuous speech recognition.
[0042] In this embodiment, the application program further includes a large vocabulary speech recognition system, and the large vocabulary speech recognition system adopts statistical pattern recognition technology.
[0043] A typical speech recognition system based on statistical pattern recognition methods consists of the following basic modules:
[0044] 1. Signal processing and feature extraction module
[0045] Second, the acoustic model
[0046] Three, pronunciation dictionary
[0047] Four, language model
[0048] Five, decoder
[0049] The main task of the signal processing and feature extraction module is to extract features from the input signal for acoustic model processing. At the same time, it generally also includes some signal processing techniques to minimize the impact of environmental noise, speakers and other factors on the features.
[0050] The acoustic model is modeled based on a first-order hidden Markov model.
[0051] The pronunciation dictionary contains vocabulary sets that can be processed by the system and their pronunciation.
[0052] The pronunciation dictionary actually provides the mapping between the acoustic model modeling unit and the language model modeling unit.
[0053] The language model models the language targeted by the system. Theoretically, various language models including regular languages ​​and context-free grammars can be used as language models. The present invention utilizes statistics-based N-grams and their variants.
[0054] The decoder is one of the cores of the speech recognition system. Its task is to find the word string that can output the signal with the greatest probability according to the acoustics, language model and dictionary on the input signal.
[0055] Step S240: Execute the target instruction corresponding to the voice instruction through an instruction execution module.
[0056] Figure 3 to 7 It is a schematic diagram of a voice command management process according to an embodiment of the present invention.
[0057] in image 3 In this case, a user sends a voice command 301 of "Call Dad" to the mobile phone 302.
[0058] in Figure 4 What is to be expressed is that the mobile phone receives a voice command through a voice receiving module, and compares the voice command with a feature parameter of a pre-input voice sample through a voice feature similarity judgment module; When the voice command 301 is issued by the person, a voice recognition module compares the voice command with a pre-input command sample to determine a target command corresponding to the voice command, and executes the corresponding voice command by a command execution module. The target instruction of the instruction, dial the phone to Dad.
[0059] in Figure 5 In, a user sends a voice command 501 of "call home now" to the mobile phone 502.
[0060] in Image 6 In the mobile phone, a voice command is received through a voice receiving module; a voice feature similarity judgment module is used to compare whether the voice command matches a feature parameter of a pre-input voice sample; when it is determined that the voice command 02 is the person When it is issued, a voice recognition module compares the voice command with a pre-input command sample, it is impossible to determine a command corresponding to the voice command, and a message that the voice command cannot be fully recognized is displayed.
[0061] in Figure 7 In, use the keywords "call" and "home" in the voice command as a combination to ask the user if they want to call home.
[0062] The above are only the preferred embodiments of the present invention and do not limit the present invention in any form. Although the present invention has been disclosed in the preferred embodiments, it is not intended to limit the present invention. Anyone familiar with the profession Those skilled in the art, without departing from the scope of the technical solution of the present invention, can use the technical content disclosed above to make slight changes or modifications to equivalent embodiments with equivalent changes, but any content that does not depart from the technical solution of the present invention is based on the present invention Any simple modifications, equivalent changes and modifications made to the above embodiments are still within the scope of the technical solutions of the present invention.

PUM

no PUM

Description & Claims & Application Information

We can also present the details of the Description, Claims and Application information to help users get a comprehensive understanding of the technical details of the patent, such as background art, summary of invention, brief description of drawings, description of embodiments, and other original content. On the other hand, users can also determine the specific scope of protection of the technology through the list of claims; as well as understand the changes in the life cycle of the technology with the presentation of the patent timeline. Login to view more.
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