Audio noise real-time detection method based on sparse decomposition

A sparse decomposition and real-time detection technology, applied in speech analysis, instruments, etc., can solve problems that have not been reported, and achieve the effect of simple algorithm and fast processing

Inactive Publication Date: 2014-12-10
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Sparse decomposition methods have been applied to the denoising of audio and video signals, but their application in noise detection has not been reported

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
  • Audio noise real-time detection method based on sparse decomposition
  • Audio noise real-time detection method based on sparse decomposition
  • Audio noise real-time detection method based on sparse decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In this embodiment, an actual broadcasted "car purchase advertisement" audio is used as input. The sampling rate of this audio segment is 48KHz, and the duration is 20 seconds. The first 8 seconds are normal audio of human voice plus background music. From the 9th second, it is disturbed by the environment, and strong interference noise is generated in the audio, which makes the human voice content It becomes blurry and cannot be heard normally. The interfering noise lasted for a total of 6 seconds. At the 15th second of the entire audio, the signal was completely interrupted, and the audio became white noise. The time-domain waveform diagram of the entire test audio is as follows figure 2 shown. The audio data is divided into audio frames equally according to the length of 512 sampling points, and the total number of frames is 1875 frames. The specific steps for noise detection of audio are as follows:

[0040] S1. Build the initial atomic library:

[0041] S11. I...

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 provides an audio noise real-time detection method based on sparse decomposition, which is used for performing real-time noise detection on audio streams. The method comprises the following steps: receiving first N frames of audio frames for constructing an initial atom library; performing mute judgment, first sparse decomposition and second sparse decomposition on each audio frame after an Nth frame, circularly counting the audio frames by adopting a frame counter, performing noise judgment once the frame counter counts to N, and meanwhile resetting the frame counter. The audio noise real-time detection method can be used for detecting various kinds of noises such as white noise, pink noise and high-frequency channel noise in audios; when a signal and noise coexist, the situations of blur audio content and failure in normally listening since the signal is covered by the noise can be avoided; meanwhile, the detection method is simple, is high in processing speed, and can be widely applied to real-time monitoring of audio signals such as broadcast signals and television signals.

Description

technical field [0001] The invention belongs to the technical field of digital audio processing, in particular to an audio noise detection method based on sparse decomposition. The method can be applied to automatic real-time monitoring of audio signals. Background technique [0002] Today, audio broadcasting has become the most popular medium of publicity and entertainment. Due to the complexity of the broadcasting system itself and the influence of external factors in the transmission, transmission and reception links, there are often broadcast anomalies or failures in broadcasting. Therefore, normal and safe broadcasting has always been a basic goal of broadcasting station business, and an important means to achieve this goal is to effectively monitor the quality of broadcasting audio. At present, domestic radio broadcasting monitoring has transitioned from the traditional manual method to computer-aided completion, and the monitoring automation of some simple abnormal ...

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 & AuthorityApplications(China)
IPC IPC(8): G10L21/0224G10L21/0308G10L25/84
Inventor甘涛何艳敏黄晓革兰刚周南
OwnerUNIV OF ELECTRONICS SCI & TECH OF CHINA