Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Self-adaptation voice detection method based on multi-domain joint estimation

A technology of speech detection and joint estimation, applied in speech analysis, speech recognition, instruments, etc., can solve the problems of inability to correctly detect the start and end points of speech signals, single detection target, single background noise, etc., and achieve high accuracy and reliability Good, the effect of improving robustness

Active Publication Date: 2014-06-11
THE 36TH INST OF CENT MILITARY COMMISSION EQUIP DEV DEPT
View PDF10 Cites 47 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0035] Therefore, because the existing detection technology has a single detection target and a single background noise, if it is applied in a complex environment, the detection effect is very poor, and the start and end points of the speech signal cannot be detected correctly.

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
  • Self-adaptation voice detection method based on multi-domain joint estimation
  • Self-adaptation voice detection method based on multi-domain joint estimation
  • Self-adaptation voice detection method based on multi-domain joint estimation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Such as figure 1 As shown, the present invention is based on the adaptive speech detection method of multi-domain joint estimation, comprises the following steps:

[0058] 10) Signal preprocessing: filter, sample, quantize, frame and window the input signal to obtain the preprocessed signal;

[0059] Such as figure 2 As shown, the signal preprocessing (10) step includes:

[0060] 11) Filtering: filter out the high-frequency pulse noise in the input voice signal, and effectively reduce the interference of signals outside the frequency band of the voice signal;

[0061] 12) Sampling and quantization: Sampling and quantizing the processing signal at a sampling rate greater than twice the highest frequency of the processing signal;

[0062] 13) Framing: Divide the voice signal into frames according to a signal duration of 20ms and an overlapping length of 10ms;

[0063] 14) Windowing: Windowing is performed on each frame of the speech signal to obtain a preprocessed s...

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 self-adaptation voice detection method based on multi-domain joint estimation. Voice can be detected in a complex environment in a self-adaptation mode, accuracy and reliability are good, and the complexity of detection is low. The voice detection method includes the steps of signal preprocessing, frequency spectrum stability judging, stable noise voice detecting, non-stable noise voice detecting and voice segment signal outputting.

Description

technical field [0001] The invention belongs to the technical field of speech detection, in particular to an adaptive speech detection method based on multi-domain joint estimation. Background technique [0002] Multiple generations of existing communication equipment coexist, and the communication frequency bands, modulation methods, data rates, and data frame formats are different, making it difficult to achieve direct interconnection and intercommunication; the communication environment is complex and changeable, and it is more difficult to guarantee voice communication. Speech detection technology is the front end of speech signal processing, which directly affects subsequent processing such as speech recognition, speech enhancement, and speaker recognition, and plays an important role in speech communication. [0003] Speech detection technology can be roughly divided into two categories: threshold comparison method and model matching method. The threshold comparison m...

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): G10L25/84G10L15/08G10L19/02
Inventor 范建华王统祥吕遵明万留进成洁
Owner THE 36TH INST OF CENT MILITARY COMMISSION EQUIP DEV DEPT
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
Eureka Blog
Learn More
PatSnap group products