CN113380274A - Smart broadcast audio quality evaluation noise detection method - Google Patents
Smart broadcast audio quality evaluation noise detection method Download PDFInfo
- Publication number
- CN113380274A CN113380274A CN202110653954.2A CN202110653954A CN113380274A CN 113380274 A CN113380274 A CN 113380274A CN 202110653954 A CN202110653954 A CN 202110653954A CN 113380274 A CN113380274 A CN 113380274A
- Authority
- CN
- China
- Prior art keywords
- equipment
- channel
- detected
- audio
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 104
- 238000013441 quality evaluation Methods 0.000 title abstract description 8
- 239000013598 vector Substances 0.000 claims abstract description 96
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000009432 framing Methods 0.000 claims abstract description 17
- 230000005856 abnormality Effects 0.000 claims description 55
- 230000002159 abnormal effect Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 26
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 3
- 230000005236 sound signal Effects 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 claims 1
- 238000007689 inspection Methods 0.000 abstract description 2
- 230000001360 synchronised effect Effects 0.000 abstract description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/60—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for measuring the quality of voice signals
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04H—BROADCAST COMMUNICATION
- H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
- H04H60/29—Arrangements for monitoring broadcast services or broadcast-related services
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The invention discloses a method for detecting noise in intelligent broadcast audio quality evaluation, which comprises the steps of firstly forming audio data of each channel of equipment to be detected into an audio group to be detected, then collecting audio data of a reference channel of reference equipment, and carrying out time domain framing and feature extraction processing on the audio data in the audio group to be detected and the audio data of the reference channel to obtain a plurality of frame feature vectors of each channel of the equipment to be detected. By adopting the detection method designed by the invention, the broadcast audio can be comprehensively detected, not only can the manual inspection work be greatly compressed, the labor cost is saved, the efficiency is improved, but also the accuracy of detecting the audio quality of the multi-channel synchronous audio acquisition equipment is greatly improved, and the audio abnormity detection result in each channel equipment is obtained by calculating the correlation of the audio data acquired by each channel; the same problems of all channels of the equipment to be detected and detection abnormity caused by various noises are avoided.
Description
Technical Field
The invention relates to the technical field of audio detection, in particular to an intelligent broadcast audio quality evaluation noise detection method.
Background
The broadcast is a news spreading tool for transmitting sound through radio waves or wires, and is produced in the 20 th century, wherein the broadcast is called wireless broadcast for transmitting programs through radio waves and is called wired broadcast for transmitting programs through wires, and has the advantages of wide objects, quick transmission, various functions and strong infectivity; the short spot is one-time passing, sequential listening cannot be selected, and listening is difficult if the language is not communicated, at present, broadcasting further realizes a strategic target mainly comprising frequency modulation and medium wave and secondarily comprising short wave, which is a significant transformation in the history of international broadcasting, and audio quality evaluation noise detection needs to be carried out on broadcasting audio before broadcasting playing, but the existing detection mode generally adopts manual sampling detection, so that not only is the efficiency low, but also the accuracy of a detection result cannot be ensured.
Disclosure of Invention
The invention aims to provide an intelligent broadcast audio quality evaluation noise detection method, which is used for solving the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a noise detection method for intelligent broadcast audio quality evaluation comprises the following steps:
firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained;
performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel;
thirdly, judging whether each channel of the equipment to be detected is abnormal or not according to the plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormity in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel;
and (IV) generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Preferably, in the first step, when time domain framing and feature extraction processing are performed on the audio data in the audio group to be detected and the audio data of the reference channel, a differential sequence of the audio signal to be detected is obtained through a plurality of audio frames, and the differential sequence is used for indicating the difference degree between the plurality of audio frames; performing autocorrelation operation on the differential sequence, and acquiring a plurality of correlation values from an autocorrelation operation result; combining the plurality of correlation values into the sequence of correlation values.
Preferably, the correlation values of the audio to be detected include: dividing the correlation value sequence into a plurality of sequence vectors according to a preset vector dimension, obtaining correlation coefficients of two adjacent sequence vectors in the plurality of sequence vectors, and determining an average value of the correlation coefficients of the two adjacent sequence vectors in the plurality of sequence vectors as an average correlation coefficient of the correlation value sequence.
Preferably, in the first step, a voice activity detection algorithm is used to remove non-voice segments in the audio data of the reference channel and non-voice segments in the audio data of each channel of the device to be detected.
Preferably, the standard threshold values of the plurality of frame feature vectors of the reference channel in the first step include a first threshold value and a second threshold value.
Preferably, the target channel in the second step is any one of a plurality of channels of the device to be detected.
Preferably, in the second step, frame correlation coefficients of every two channels of the device to be detected are calculated by using frame feature vectors of every two channels of the device to be detected, the frame correlation coefficients of every two channels of the device to be detected form a frame correlation coefficient matrix of the device to be detected, whether the frame correlation coefficient in the frame correlation coefficient matrix of the device to be detected is greater than a first preset threshold value or not is judged, and if yes, 1 is used as a judgment result of the channel corresponding to the frame correlation coefficient; and if not, taking 0 as the judgment result of the channel corresponding to the frame correlation coefficient.
Preferably, in the third step, the sum of the judgment results of each channel and other channels of the device to be detected is counted, whether the sum of the judgment results of each channel and other channels of the device to be detected is greater than a preset value or not is judged, if yes, 1 is used as the in-device detection result of the channel of the device to be detected, and if not, 0 is used as the in-device detection result of the channel of the device to be detected; and when the number of the in-device detection results of the detection device channel which are continuously 1 exceeds N, judging the channel to be abnormal, setting the in-device audio abnormality detection result of the channel to be 1, and otherwise, setting the in-device audio abnormality detection result of the channel to be 0.
Preferably, in the fourth step, the frame feature vector of the reference channel and the frame feature vector of the target channel of the device to be detected are used to calculate the frame correlation coefficient between the reference channel and the target channel of the device to be detected.
Preferably, in the fourth step, it is determined whether a frame correlation coefficient between the reference channel and the target channel of the device to be detected is greater than a second preset threshold, and if so, 1 is taken as an inter-device decision result of the target channel; and if not, taking 0 as the inter-device judgment result of the target channel.
Compared with the prior art, the invention has the following beneficial effects:
by adopting the detection method designed by the invention, the broadcast audio can be comprehensively detected, not only can the manual inspection work be greatly compressed, the labor cost is saved, the efficiency is improved, but also the accuracy of detecting the audio quality of the multi-channel synchronous audio acquisition equipment is greatly improved, and the audio abnormity detection result in each channel equipment is obtained by calculating the correlation of the audio data acquired by each channel; the same problems of all channels of the equipment to be detected and detection abnormity caused by various noises are avoided.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a technical scheme that:
a noise detection method for intelligent broadcast audio quality evaluation comprises the following steps:
firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained;
performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel;
thirdly, judging whether each channel of the equipment to be detected is abnormal or not according to the plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormity in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel;
and (IV) generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
The first embodiment is as follows:
firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example two:
in the first embodiment, the following steps are added:
step one, when time domain framing and feature extraction processing are carried out on audio data in an audio group to be detected and audio data of a reference channel, a differential sequence of an audio signal to be detected is obtained through a plurality of audio frames, and the differential sequence is used for indicating the difference degree among the plurality of audio frames; performing autocorrelation operation on the differential sequence, and acquiring a plurality of correlation values from an autocorrelation operation result; combining the plurality of correlation values into the sequence of correlation values.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example three:
in the second embodiment, the following steps are added:
the correlation values of the audio to be detected include: dividing the correlation value sequence into a plurality of sequence vectors according to a preset vector dimension, obtaining correlation coefficients of two adjacent sequence vectors in the plurality of sequence vectors, and determining an average value of the correlation coefficients of the two adjacent sequence vectors in the plurality of sequence vectors as an average correlation coefficient of the correlation value sequence.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example four:
in the third embodiment, the following steps are added:
in the first step, a voice activity detection algorithm is used for removing non-voice sections in the audio data of the reference channel and non-voice sections in the audio data of each channel of the equipment to be detected.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example five:
in the fourth example, the following steps were added:
the standard threshold values of the plurality of frame feature vectors of the reference channel in the first step comprise a first threshold value and a second threshold value.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example six:
in the fifth example, the following steps were added:
and the target channel in the step two is any one of a plurality of channels of the equipment to be detected.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example seven:
in example six, the following steps were added:
calculating frame correlation coefficients of every two channels of the equipment to be detected by using frame feature vectors of every two channels of the equipment to be detected, wherein the frame correlation coefficients of every two channels of the equipment to be detected form a frame correlation coefficient matrix of the equipment to be detected, judging whether the frame correlation coefficients in the frame correlation coefficient matrix of the equipment to be detected are larger than a first preset threshold value or not, and if so, taking 1 as a judgment result of the channel corresponding to the frame correlation coefficients; and if not, taking 0 as the judgment result of the channel corresponding to the frame correlation coefficient.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example eight:
in example seven, the following steps were added:
counting the sum of judgment results of each channel and other channels of the equipment to be detected, judging whether the sum of the judgment results of each channel and other channels of the equipment to be detected is larger than a preset value, if so, taking 1 as an in-equipment detection result of the channel of the equipment to be detected, and if not, taking 0 as an in-equipment detection result of the channel of the equipment to be detected; and when the number of the in-device detection results of the detection device channel which are continuously 1 exceeds N, judging the channel to be abnormal, setting the in-device audio abnormality detection result of the channel to be 1, and otherwise, setting the in-device audio abnormality detection result of the channel to be 0.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example nine:
in example eight, the following steps were added:
and in the fourth step, the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected are used for calculating the frame correlation coefficient of the reference channel and the target channel of the equipment to be detected.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Example ten:
in example nine, the following procedure was added:
judging whether the frame correlation coefficient of the reference channel and the target channel of the device to be detected is greater than a second preset threshold value or not, if so, taking 1 as an inter-device judgment result of the target channel; and if not, taking 0 as the inter-device judgment result of the target channel.
Firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained; performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel; judging whether each channel of the equipment to be detected is abnormal according to a plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormality in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel; and generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A noise detection method for intelligent broadcast audio quality assessment is characterized in that: the method comprises the following steps:
firstly, the collected audio data of each channel of the equipment to be detected form an audio group to be detected, then the audio data of a reference channel of reference equipment is collected, time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, and a plurality of frame feature vectors of each channel of the equipment to be detected and a plurality of frame feature vectors of the reference channel are obtained;
performing correlation calculation and frame correlation judgment by using the frame characteristic vector of each channel of the equipment to be detected to obtain a plurality of judgment results of each channel of the equipment to be detected, and performing correlation calculation and frame correlation judgment by using the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected to obtain a plurality of inter-equipment judgment results of the target channel;
thirdly, judging whether each channel of the equipment to be detected is abnormal or not according to the plurality of judgment results of each channel of the equipment to be detected, and obtaining the detection result of the audio abnormity in the equipment of each channel of the equipment to be detected; judging whether the target channel of the equipment to be detected is abnormal or not according to the judgment results among the plurality of pieces of equipment of the target channel, and obtaining the detection result of the audio abnormality among the pieces of equipment of the target channel;
and (IV) generating an audio detection report according to the in-equipment audio abnormality detection result of each channel of the equipment to be detected and the inter-equipment audio abnormality detection result of the target channel.
2. The method of claim 1, wherein the method comprises: in the first step, when time domain framing and feature extraction processing are carried out on the audio data in the audio group to be detected and the audio data of the reference channel, a differential sequence of the audio signal to be detected is obtained through a plurality of audio frames, and the differential sequence is used for indicating the difference degree among the plurality of audio frames; performing autocorrelation operation on the differential sequence, and acquiring a plurality of correlation values from an autocorrelation operation result; combining the plurality of correlation values into the sequence of correlation values.
3. The method of claim 2, wherein the method comprises: the correlation values of the audio to be detected comprise: dividing the correlation value sequence into a plurality of sequence vectors according to a preset vector dimension, obtaining correlation coefficients of two adjacent sequence vectors in the plurality of sequence vectors, and determining an average value of the correlation coefficients of the two adjacent sequence vectors in the plurality of sequence vectors as an average correlation coefficient of the correlation value sequence.
4. The method of claim 1, wherein the method comprises: in the first step, a voice activity detection algorithm is used for removing non-voice sections in the audio data of the reference channel and non-voice sections in the audio data of each channel of the equipment to be detected.
5. The method of claim 1, wherein the method comprises: the standard threshold values of the plurality of frame feature vectors of the reference channel in the first step comprise a first threshold value and a second threshold value.
6. The method of claim 1, wherein the method comprises: and the target channel in the second step is any one of a plurality of channels of the equipment to be detected.
7. The method of claim 1, wherein the method comprises: in the second step, frame correlation coefficients of every two channels of the equipment to be detected are calculated by using frame feature vectors of every two channels of the equipment to be detected, the frame correlation coefficients of every two channels of the equipment to be detected form a frame correlation coefficient matrix of the equipment to be detected, whether the frame correlation coefficients in the frame correlation coefficient matrix of the equipment to be detected are larger than a first preset threshold value or not is judged, and if yes, 1 is used as a judgment result of the channel corresponding to the frame correlation coefficients; and if not, taking 0 as the judgment result of the channel corresponding to the frame correlation coefficient.
8. The method of claim 1, wherein the method comprises: counting the sum of the judgment results of each channel and other channels of the equipment to be detected, judging whether the sum of the judgment results of each channel and other channels of the equipment to be detected is larger than a preset value, if so, taking 1 as the in-equipment detection result of the channel of the equipment to be detected, and if not, taking 0 as the in-equipment detection result of the channel of the equipment to be detected; and when the number of the in-device detection results of the detection device channel which are continuously 1 exceeds N, judging the channel to be abnormal, setting the in-device audio abnormality detection result of the channel to be 1, and otherwise, setting the in-device audio abnormality detection result of the channel to be 0.
9. The method of claim 1, wherein the method comprises: and in the fourth step, the frame characteristic vector of the reference channel and the frame characteristic vector of the target channel of the equipment to be detected are used for calculating the frame correlation coefficient of the reference channel and the target channel of the equipment to be detected.
10. The method of claim 9, wherein the method comprises: judging whether the frame correlation coefficient of the reference channel and the target channel of the device to be detected is greater than a second preset threshold value or not in the fourth step, and if so, taking 1 as an inter-device judgment result of the target channel; and if not, taking 0 as the inter-device judgment result of the target channel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110653954.2A CN113380274A (en) | 2021-06-11 | 2021-06-11 | Smart broadcast audio quality evaluation noise detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110653954.2A CN113380274A (en) | 2021-06-11 | 2021-06-11 | Smart broadcast audio quality evaluation noise detection method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113380274A true CN113380274A (en) | 2021-09-10 |
Family
ID=77574028
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110653954.2A Pending CN113380274A (en) | 2021-06-11 | 2021-06-11 | Smart broadcast audio quality evaluation noise detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113380274A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106782614A (en) * | 2016-12-26 | 2017-05-31 | 广州酷狗计算机科技有限公司 | Sound quality detection method and device |
CN107170465A (en) * | 2017-06-29 | 2017-09-15 | 数据堂(北京)科技股份有限公司 | A kind of audio quality detection method and audio quality detecting system |
CN112151055A (en) * | 2020-09-25 | 2020-12-29 | 北京猿力未来科技有限公司 | Audio processing method and device |
-
2021
- 2021-06-11 CN CN202110653954.2A patent/CN113380274A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106782614A (en) * | 2016-12-26 | 2017-05-31 | 广州酷狗计算机科技有限公司 | Sound quality detection method and device |
CN107170465A (en) * | 2017-06-29 | 2017-09-15 | 数据堂(北京)科技股份有限公司 | A kind of audio quality detection method and audio quality detecting system |
CN112151055A (en) * | 2020-09-25 | 2020-12-29 | 北京猿力未来科技有限公司 | Audio processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10068586B2 (en) | Binaurally integrated cross-correlation auto-correlation mechanism | |
EP2257943B1 (en) | Audio visual signature, method of deriving a signature, and method of comparing audio-visual data | |
US8843349B2 (en) | Apparatus for removing the partial discharge noise of an electrical power facility and apparatus for detecting a partial discharge generated section | |
EP3163574B1 (en) | Method and apparatus for detecting abnormal frame | |
US7508948B2 (en) | Reverberation removal | |
KR20180063282A (en) | Method, apparatus and storage medium for voice detection | |
CN107170465B (en) | Audio quality detection method and audio quality detection system | |
US8891786B1 (en) | Selective notch filtering for howling suppression | |
JP5605574B2 (en) | Multi-channel acoustic signal processing method, system and program thereof | |
CN105573104A (en) | Watch detection noise reduction method based on improved EMD | |
CN115165079A (en) | Equipment alarm method based on multiple sound characteristic analysis | |
CN113380274A (en) | Smart broadcast audio quality evaluation noise detection method | |
CN112597958B (en) | Automatic identification method and system for rolling bearing fault | |
CN108055088B (en) | Abnormal radio signal monitoring method and device and radio monitoring equipment | |
US9739866B2 (en) | Method and apparatus for radio direction finding | |
CN111083627B (en) | Fault microphone detection method and device | |
CN110310661B (en) | Method for calculating two-path real-time broadcast audio time delay and similarity | |
Pirhosseinloo et al. | Time-Frequency Masking for Blind Source Separation with Preserved Spatial Cues. | |
CN113824518A (en) | Non-cooperative signal detection method based on frequency spectrum | |
CN110376436B (en) | Multi-scale noise power spectral line spectrum detection method | |
CN111786736A (en) | Single-bit receiver signal processing method based on compensation algorithm | |
US5926553A (en) | Method for measuring the conservation of stereophonic audio signals and method for identifying jointly coded stereophonic audio signals | |
CN117061039B (en) | Broadcast signal monitoring device, method, system, equipment and medium | |
CN111355514B (en) | Spread spectrum detection method for direct spread spectrum signal | |
CN116312447B (en) | Directional noise elimination method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |