Voice signal endpoint detection method, device, device and storage medium
A voice signal and endpoint detection technology, applied in voice analysis, voice recognition, instruments, etc., can solve the problems of low detection accuracy, poor detection accuracy, large amount of calculation, etc., and achieve the effect of improving detection efficiency
Active Publication Date: 2021-09-28
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] There are mainly two existing VAD detection methods: one is the VAD detection method based on energy and zero-crossing rate. In the case of the detection accuracy is very low
Another detection method is based on the VAD detection method of deep learning. This method has higher accuracy, but the calculation load is relatively large, and the performance requirements of the equipment are relatively high.
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
[0018] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the drawings, it should be understood that the application may be embodied in various forms and should not be construed as limited to the embodiments set forth herein; A more thorough and complete understanding of the application. It should be understood that the drawings and embodiments of the present application are for exemplary purposes only, and are not intended to limit the protection scope of the present application.
[0019] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of the embodiments of the present application and the above drawings are used to distinguish similar objects, while It is not necessarily used to describe a particular order or sequence. It is to be understood that the data so used are interchangeable under app...
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 embodiment of the present application provides a voice signal endpoint detection method, device, device and storage medium, by acquiring the first audio signal, the first audio signal includes the voice signal; first voice activity detection based on energy and zero-crossing rate VAD algorithm, and one of the second VAD algorithms based on deep learning detects the starting point of the speech signal from the first audio signal; after detecting the starting point of the speech signal, adopts the first VAD algorithm and the other of said second VAD algorithm detects the end of said speech signal. Therefore, while ensuring the detection accuracy of the voice signal endpoint, the amount of calculation is reduced.
Description
technical field [0001] The embodiments of the present application relate to the technical field of voice detection, and in particular, to a voice signal endpoint detection method, device, device, and storage medium. Background technique [0002] Voice Activity Detection (VAD for short), also known as voice endpoint detection, is usually used in voice interaction scenarios to detect user voices, so as to perform corresponding control or voice interaction operations based on user voices. [0003] There are mainly two existing VAD detection methods: one is the VAD detection method based on energy and zero-crossing rate. In this case, the detection accuracy is very low. Another detection method is the VAD detection method based on deep learning. This method has higher accuracy, but has a large amount of calculation and requires higher performance of the device. Contents of the invention [0004] Embodiments of the present application provide a voice signal endpoint detection...
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): G10L15/04G10L15/06G10L15/18G10L21/02G10L25/87
CPCG10L21/0202G10L15/04G10L15/06G10L15/1822G10L25/87
Inventor 李超朱唯鑫孙建伟
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD