Distributed voiceprint recognition method and device based on wavelet transformation
A wavelet transform and voiceprint recognition technology, applied in speech analysis, instruments, etc., can solve the problems of high computational complexity and low recognition efficiency, and achieve the effect of improving recognition efficiency and ensuring accuracy
Inactive Publication Date: 2017-07-04
CHINA TELECOM CORP LTD
View PDF6 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The technical problem to be solved by the present invention is that in the existing voiceprint recognition based on wavelet transform, full information matching leads to high computational complexity and low recognition efficiency
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
[0022] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangements of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
[0023] At the same time, it should be understood that, for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.
[0024] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way taken as limiting the invention, its application or uses.
[0025] Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part of the Authoriz...
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 discloses a distributed voiceprint recognition method and a distributed voiceprint recognition device based on wavelet transformation, relating to the field of speech recognition. The method comprises the following steps: carrying out wavelet transformation on to-be-recognized speech signals, so that hierarchical feature parameters of the to-be-recognized speech signals are extracted, wherein the hierarchical feature parameters comprise low-frequency feature parameters and high-frequency feature parameters; judging that whether the low-frequency feature parameters are matched with low-frequency signals in a testing voice library or not; and if the low-frequency feature parameters are matched with the low-frequency signals in the testing voice library, carrying out accurate match reorganization on the high-frequency feature parameters and high-frequency signals in the testing voice library. For the method and the device, the step-by-step identification is adopted, namely, the low-frequency signal part with small calculation amount is identified first, and a not matched feature template is rapidly eliminated; if the low-frequency features are matched, the accurate match recognition is carried out aiming at the integral voiceprint features, therefore, while the accuracy is guaranteed, the recognition efficiency is improved.
Description
technical field [0001] The invention relates to the field of speech recognition, in particular to a distributed voiceprint recognition method and device based on wavelet transform. Background technique [0002] Speech signal is essentially a non-stationary signal, and wavelet transform is not subject to short-term stationary constraints, so it can effectively extract dynamic voiceprint features. As a biometric feature, voiceprint is mostly used in identity recognition, requiring fast and real-time authentication. However, the speed of current algorithm recognition cannot meet business needs. For example, in the existing voiceprint recognition based on wavelet transform, full information matching leads to high computational complexity and low recognition efficiency, which leads to slow response time when the voiceprint library is large, which is not enough to meet business needs and reduce positioning accuracy. Contents of the invention [0003] The technical problem to be...
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): G10L17/02G10L17/06
CPCG10L17/02G10L17/06
Inventor 赵静陈新河李慧芳
Owner CHINA TELECOM CORP LTD