Signal processing method and terminal equipment

A signal processing and terminal equipment technology, applied in voice analysis, voice recognition, instruments, etc., can solve problems such as failure to work normally, potential safety hazards of user voice interaction, and inability to accurately distinguish between real voice and recorded voice, etc. Achieve the effect of improving accuracy, improving user experience, and realizing effective recognition

Pending Publication Date: 2019-05-14
BEIJING SAMSUNG TELECOM R&D CENT +1
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 1) The existing Gaussian Mixture Model-based speaker recognition system (GMM-UBM) cannot accurately distinguish between real speech and recorded speech, so it cannot resist ultrasonic attacks
[0007] 2) The existing Gaussian mixture model-based speaker recognition system (GMM-UBM) can only work in a quiet environment, and cannot work normally in other complex environments
[0008] 3) The existing Support Vector Machine (SVM) or K Nearest Neighbor Classification Algorithm (KNN) based on Mel-Frequency Cepstral Coefficient (M

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
  • Signal processing method and terminal equipment
  • Signal processing method and terminal equipment
  • Signal processing method and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0178] The embodiment of the present invention discloses a method for identifying abnormal voice signals used for attack by extracting voice signal features and using machine learning to identify the voice signal features. The detailed system block diagram of this embodiment is as follows Figure 13 shown.

[0179] step:

[0180] 1. Prepare a large amount of normal speech signal and abnormal speech signal data for attack for training the network model and classifier of machine learning. The larger the amount of data, the better the stability of the network model and the discrimination of the classifier.

[0181] 2. Through the band-pass filter, extract the normal voice signal and demodulate the voice information of the abnormal voice signal used for the attack in the frequency range of 2000 Hz to 3000 Hz.

[0182] 3. Extract the short-term zero-crossing rate and short-term energy characteristics of the normal speech signal and the abnormal speech signal after passing through ...

Embodiment 2

[0186] A dynamic wake-up command is generated and notified to the user.

[0187] Dynamic instructions can be customized by the user. For example, the user can set the words or sentences for the wake-up instruction; the system can also set a set of words or sentences for the user to wake up by default; Click, and then extract keywords as words or sentences for wake-up instructions.

[0188] At present, many terminal devices can display information floatingly on the screen when they are in a standby state. Such as Figure 14 As shown, so the wake-up word can be displayed on the screen in the standby state, or displayed on the screen of the wearable device connected to it. The user sees the current wake-up command, and then wakes up the terminal by uttering the wake-up command equipment.

[0189] For example, the terminal device currently randomly selects one of the previously defined wake-up words and displays it on the screen, and the user speaks the current wake-up word whe...

Embodiment 3

[0192] The attack signals are distinguished by the characteristic changes of the signals.

[0193] This method can change the characteristics of the user's voice signal when the user initiates a voice command to the terminal device by slightly shaking the terminal device up and down, or adding gestures between the terminal device and the user. The terminal device distinguishes whether it is a normal voice signal according to the change of the signal characteristics, and responds to the voice command only if it is a normal voice signal.

[0194] In this mode, the characteristics of the input voice signal will change regularly, and if the terminal device detects that the change pattern of the characteristics of the input voice signal is consistent with the set change pattern, the voice signal is considered to be a normal voice signal , otherwise, it is regarded as an abnormal speech signal.

[0195] It is also possible to pre-train the machine learning network model for the abo...

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 relates to the technical field of speech recognition, and provides a signal processing method and terminal equipment. The signal processing method comprises the following steps: extracting feature information from an input signal; determining whether the input signal is an abnormal speech signal or not according to the extracted feature information. In the signal processing method, through the processing process of determining whether the input signal is an abnormal speech signal or not according to the feature information extracted from the input signal, so that the effective recognition of the abnormal speech signal is realized, the accuracy of recognition is improved, and the safety of voice interaction of a user is guaranteed, and the user experience is improved.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to a signal processing method and terminal equipment. Background technique [0002] Ultrasonic attack (also known as "dolphin attack") was proposed at the ACM CCS (The ACM Conference on Computer and Communications Security) conference in 2017. It is said that ultrasonic attack can break through the voice assistant application of the terminal, which makes people Questions have been raised about the safety of voice interactions. [0003] Ultrasonic attack is to use the basic principle of ultrasound, and its implementation idea is: in the attack signal modulation stage, the attack voice signal (here referred to as baseband signal) in the first frequency range (normal frequency range) is modulated so that the user cannot The range of ultrasound heard. Then, in the attack signal transmission stage, the ultrasonic transmitter is used to transmit the modulated attack voice sign...

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): G10L25/03G10L25/24G10L25/27G10L25/30G10L25/51G10L15/02
Inventor 王宪亮王立众尹成万朱恒刘长滔闵超杨磊
Owner BEIJING SAMSUNG TELECOM R&D CENT
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