Cross-channel voiceprint recognition method, device, equipment and storage medium
A voiceprint recognition and channel technology, applied in the field of geostatistics, can solve problems such as the difficulty of cross-channel voiceprint recognition, and achieve the effect of accurate recognition
Active Publication Date: 2022-03-11
TSINGHUA UNIV +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention provides a cross-channel voiceprint recognition method, device, electronic equipment and non-transient computer-readable storage medium, which are used to solve the difficult problem of cross-channel voiceprint recognition in the current technology and improve the accuracy of cross-channel voiceprint recognition
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
[0033] In order to make the objects, technical solutions, and advantages of the present invention, the technical solutions in the present invention will be apparent from the drawings of the present invention, and it will be described in connection with the drawings of the present invention. , Not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained without creative labor are not made in the premise of creative labor.
[0034] The terms used in one or more embodiments of the present invention are intended to illustrate one or more embodiments of the invention. The "one", "one" and "" ",", "" "," and "" ", as described in one or more embodiments of the present invention, are also intended to include most forms unless the context clearly represents other meanings. It is also to be understood that the terms "and / or" used in one or more embodiments of the present invention refer to any or from any or more possible combinations of o...
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 present invention provides a method, device, device and storage medium for cross-channel voiceprint identification, including: acquiring voiceprint audio data to be identified, wherein the voiceprint audio data to be identified is collected from a channel in a set channel set, and the The set channel set includes at least two different channels; the voiceprint audio data to be identified is input into a preset cross-channel voiceprint recognition model to obtain a voiceprint audio data processing result, so as to obtain a voiceprint audio data processing result according to the voiceprint audio data processing result. Perform voiceprint audio data recognition; wherein, the cross-channel voiceprint recognition model is obtained by training the voiceprint audio data collected in the set channel set through multiple iterations, and in each iteration, two different channels are used. The voiceprint audio data collected in the model is used for model parameter training. The technical scheme of the present invention can improve the recognition accuracy of cross-channel voiceprint recognition.
Description
Technical field [0001] The present invention relates to the field of statistical methods, and more particularly to a cross-channel voices recognition method, apparatus, electronic device, and non-transitory computer readable storage medium. Background technique [0002] In recent years, with the in-depth study of voiced identification technology, the sound pattern recognition system has achieved satisfactory performance performance under single channel conditions. However, in practical applications, speech signals can be transmitted through different channels, such as network channels, telephone channels, and the like. This channel difference will generate different degrees of distortion to the voice signal, affecting the performance of the sound pattern recognition system. For example, in the registration phase, user voice is acquired by network channel; in the identification phase, user voice is collected by phone channel. At this time, due to channel mismatch, the sound identi...
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 Patents(China)
IPC IPC(8): G10L17/04
CPCG10L17/04
Inventor 郑方佴瑞乾李蓝天王东张琛谢弈峥
Owner TSINGHUA UNIV