Unlock instant, AI-driven research and patent intelligence for your innovation.

Human voice detection orientation method based on microphone array plate

A Microphone Array, Human Voice Technology

Active Publication Date: 2020-01-17
西安合谱声学科技有限公司
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a microphone array-based voice detection and orientation method to solve the problems of inaccurate voice recognition and insufficient camera focus in the prior art conference system

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Human voice detection orientation method based on microphone array plate
  • Human voice detection orientation method based on microphone array plate
  • Human voice detection orientation method based on microphone array plate

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 1 with figure 2 As shown, this embodiment discloses a microphone array-based human voice detection and orientation method, which includes the following steps:

[0047] Step 1: Use the microphone array to obtain the audio signal at the sound source;

[0048] Step 2: Perform angle calculation and vocal judgment on the audio signal obtained in step 1 frame by frame, mark each frame as a noise signal or speech signal according to the judgment result, and output the frame and angle of the judgment as a speech signal until the audio signal The last frame is judged and the detection is complete;

[0049] Among them, the human voice judgment for each frame of the audio signal is executed according to the following steps:

[0050] Step 2.1: Obtain the current frame of the audio signal, and use the DOA algorithm to calculate the angle of the current frame;

[0051] Step 2.2: Calculate various attribute values ​​of the current frame, the attribute values ​​include speech e...

Embodiment 2

[0079] In this embodiment, a microphone array-based human voice detection method is disclosed. On the basis of Embodiment 1, the application of the microphone array-based human voice detection method in a video conference system is disclosed. At the same time, the microphone array The board is placed in any smart device that needs to locate the human voice, such as the application scenario of the educational recording and broadcasting system, the application scenario of the interrogation system, etc.

[0080] In this embodiment, the human voice detection method based on the microphone array is mainly used to detect whether the angle of each frame of the current audio in the conference scene is the human voice angle. If it is judged to be human voice, the angle is transmitted to the camera to drive the camera Move horizontally and realize automatic focus of the speaker through face recognition technology.

[0081] Such as image 3 As shown, the horizontal axis is the number of samp...

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

No PUM Login to View More

Abstract

The invention belongs to the technical field of acoustic signal processing, and discloses a microphone array-based human voice detection orientation method, which comprises the following steps of: 1,acquiring an audio signal at a sound source by using a microphone array; and 2, performing angle calculation and human voice judgment on the audio signal obtained in the step 1 frame by frame, markingeach frame as a noise signal or a voice signal according to a judgment result, and outputting the frame judged as the voice signal and the angle of the voice signal until the judgment of the last frame of the audio signal is finished, thereby finishing the detection. According to the invention, voice signals with large energy can be recognized with small calculation data volume. Typical meeting room noise such as table clapping, clapping and page turning can be effectively filtered out, and high use value is achieved.

Description

Technical field [0001] The invention belongs to the technical field of acoustic signal processing, and in particular relates to a method for detecting and directing human voice based on a microphone array. Background technique [0002] With the development of electronic information technology and acoustic technology, sound source directional technology based on microphone arrays is increasingly being applied to various products. For example, video conferencing systems are used in people’s daily life, along with the development of intelligence. It is becoming more and more popular in study and work. [0003] In general video conferencing systems, it is often necessary to record the audio and video of the meeting scene in real time, and it is required to quickly identify the speaker and quickly focus the camera on the speaker. At present, the focus of the camera generally needs to be achieved through manual operation by the user, which results in delayed video switching, low focus a...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G10L21/0208G10L21/0216G10L25/60G10L25/84G01S3/808
CPCG01S3/8083G10L21/0208G10L21/0216G10L25/60G10L25/84G10L2021/02087G10L2021/02166H04R2430/20
Inventor 黄绍锋孙雅蓉张升辉刘晓霞靳冠军
Owner 西安合谱声学科技有限公司