Voice processing method and device, readable storage medium and electronic equipment
A technology for speech processing and target speech, applied in the fields of devices, speech processing methods, readable storage media and electronic equipment, and can solve problems such as low accuracy
Pending Publication Date: 2021-07-06
LENOVO (BEIJING) LTD
View PDF14 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In this way, the accuracy of recognition for the received speech is low
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] The principle and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present invention, rather than to limit the scope of the present invention in any way. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
[0023] First, the application scenarios of the present invention are briefly described. The technical solutions of the present invention can be applied to smart speakers, smart homes and other smart sound devices with voice recognition and response functions. For example: for a smart speaker, when a sound signal is received through a multi-microphone array, the received sound signal is identified and processed, and when it is determined that the smart speaker ...
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 voice processing method and device, a computer readable storage medium and electronic equipment. The method comprises the steps of respectively determining the direction of arrival and the noise type of multiple branch signals when receiving a sound signal comprising the multiple branch signals from any direction in a reverberation environment, according to the direction of arrival and the noise type, determining the difference between the sound signal and a historical sound record, and extracting a target voice from the sound signal according to the historical sound record, the direction of arrival and the sound source type when the difference satisfies a first set difference condition. Therefore, when the sound signal is received, the historical sound record of the user is fully utilized, and the targeted target voice extraction can be performed on the sound signal according to the prior rule of the historical sound record, such as the use habit of the user, the relative fixed noise type and other information. Therefore, the recognition accuracy of the sound signal is effectively improved, and the wake-up and corresponding accuracy of the sound signal to the equipment is further improved.
Description
technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a voice processing method, device, readable storage medium and electronic equipment. Background technique [0002] With the development of AI (Artificial Intelligence, artificial intelligence) technology, speech recognition technology has been widely used in China, and intelligent voice interaction technology has also been greatly developed. However, at present, when many voice interaction devices perform far-field voice recognition or wake up the device, the device makes indiscriminate judgment and processing on the voices picked up from each sound source direction. The methods are the same. In this way, the accuracy of recognizing the received speech is low. Contents of the invention [0003] The application discloses a voice processing method, device, computer-readable storage medium and electronic equipment. [0004] According to the first aspect of the p...
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): G10L21/0208G10L21/0216
CPCG10L21/0208G10L21/0216
Inventor 夏光敏张琛雨张银平
Owner LENOVO (BEIJING) LTD