Recognition method and system of effective speeches
A speech recognition and speech technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of poor real-time recognition effect and low effective speech recognition rate, and achieve the effect of reliable and rapid recognition
Inactive Publication Date: 2015-04-29
SHENZHEN YUNZHIXUN NETWORK TECH
View PDF14 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] Traditional methods for recognizing effective speech are generally based on the principles of energy size, zero-crossing rate, and autocorrelation. It needs to continuously make comprehensive judgments on several speech data frames. These methods have better recognition results in fixed scenes, but for non-fixed scenes And when the scene is switched frequently, such as quiet environment to noisy office environment, bus, construction site, etc., the real-time recognition effect is poor, and the effective voice recognition rate will be greatly reduced
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] Below in conjunction with accompanying drawing and specific embodiment, the present invention will be further described:
[0047] See figure 1 , the present invention relates to a kind of effective speech recognition method, and its preferred embodiment comprises the following steps:
[0048] Step A: Obtain the speech spectrum distribution of the current speech frame in real time;
[0049] In this embodiment, step A includes the following sub-steps:
[0050] Step A1: real-time according to Fourier transform current speech frame is transformed into speech frequency domain; Preferably, current speech is changed to speech frequency domain X (k) according to formula 1, and formula 1 is X (k)=FFT ( x(j)), j ∈ (0, N) is the sample number in the time domain, and k ∈ (0, N) is the sample number in the frequency domain.
[0051] Step A2: Obtain the energy at each frequency spectrum of the speech frequency domain;
[0052] Preferably, calculate the energy E (k) at each freque...
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
Login to View More Abstract
The invention relates to a recognition method and system of effective speeches. The method includes the steps of A, acquiring in real time speech spectral distribution of a current speech frame; B, acquiring in real time short-term energy and long-term energy of the current speech frame; C, acquiring speech similarity according to the speech spectral distribution, the long-term energy and the short-term energy; D, judging whether or not the speech similarity is higher than a preset speech similarity threshold; if yes, executing a step E; if not, executing a step F; E, determining that the current speech frame is an effective speech; F, determining that the current speech frame is a non-speech. According to the method, the speech spectral distribution and energy change of each speech frame is acquired in real time, the effective speech is quickly recognized according to the speech spectral distribution and energy change, comprehensive judgment of the traditional method depending on multiple frames is not required, and recognizing is reliably and quickly performed even when application scenes are in frequent switching.
Description
technical field [0001] The invention relates to an effective voice recognition method and system. Background technique [0002] Traditional methods for recognizing effective speech are generally based on the principles of energy size, zero-crossing rate, and autocorrelation. It needs to continuously make comprehensive judgments on several speech data frames. These methods have better recognition results in fixed scenes, but for non-fixed scenes And when the scene is frequently switched, such as a quiet environment to a noisy office environment, in a bus, on a construction site, etc., the real-time recognition effect is poor, and the effective voice recognition rate will be greatly reduced. Contents of the invention [0003] Aiming at the deficiencies of the prior art, the present invention aims to provide an effective speech recognition method and system that can solve the above technical problems. [0004] To achieve the above object, the present invention adopts the fol...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G10L15/20
Inventor 付姝华
Owner SHENZHEN YUNZHIXUN NETWORK TECH