Audio Analytics Aggression Tested

Author: Ethan Ace, Published on Nov 20, 2015

What if you could use your IP cameras to detect fights before they start? 

That is the goal of Louroe / Sound Intelligence with their recently released Aggression Detector audio analytics. Claiming that "90% of physical aggression are preceded by verbal aggression", these analytics are designed to alert guards before verbal altercations turn physical.

We tested the Aggression Detector using both live subjects and recorded clips of multiple scenes, to see just how these analytics perform.

Here is the app main view that we used to monitor and optimize the audio analytics:

**** ** *** ***** *** **** ** ******* ** ****** fights ****** **** *****? 

**** ** *** **** ******** / ***** **************** ***** ******** ****************** ******** ***** *********. ******** **** "**% ** ******** ********** *** ******** ** verbal **********", ***** ********* *** ******** ** ***** ****** ****** verbal ************ **** ********.

** ****** *** ********** ******** ***** **** **** ******** *** ******** clips ** ******** ******, ** *** **** *** ***** ********* perform.

**** ** *** *** **** **** **** ** **** ** ******* and ******** *** ***** *********:

[***************]

*******

******/***** ************ ********** ******** ********* *** * *********** ****** ******** to ************ *******, ********* ***** ** ****** ***** *** ********* go *********, ******** ****** ******/************ ********. 

*******, **** *** *** ******** *** *** *********, *** *** best **** ** ******** ***** *****, ** ****** ** ******** ******** will ******* ******** ***** ******, ***** **** ********** ***** ****** reduce analytics' ******* ** *********** ******. 

Key ********

** *** *****, ******'* ********** ********* *********** ** ***** *********** over *** ****** ** ***** **** ** ******* **** ****** area (**** ****** ***** *************, ****** ******* **** *** ***** ** other *******, ** ***** ***********).

*******, **** ***-********** ****** ******** ****** ***** ****** ** ******* degrees:

  • *****/***** *****:***** ****** *** ****** ********* **** ******** ***** ******, ********** of ***********. ****** ********** *** ***** ********** ********* ** ***** applications.
  • ****, ***-********** ******: ** **** *****, ****** ***-********** ******, ******, etc., ********* ******. **** *** ******** *** ******** * *** times (

********* ******** ********** ******** ****** ** ******* *** *******. ***** shouts ** **** ****** ***** ********* ********* ****** *** *****.

****** ******** ***** *** ** **** ** **** *********** *** best ***********. ******** **** *** *** *********** *** ********* ****** in *** *****, **** **** ********** ***** ****** *********** ******** detection ***********. 

** ****** *** ***** ***********. *** ****** ******* ** ******* I/O *** ** ****.

*******

**** *** ******'* ********** ********* ** $*** *** *******.

Potential ************

*** **** *** *** ***** ********** ********* ** ** ******** quiet ***** ***** ********** ****** **** ****** ****** *** ******* background *****, ********* *******, *********, ****** ********, **********, ***.

***** ********* ***** ** ****** ** *******, *** *** ********* volume *** ***** ***** ** ****** ***** ******/***** ** ** between ******* **** ****** ******* ******** ***** ******. ***** ***** *** be *** ******* ** ***** **** *******, *** **** ***** largely ****** *** ******** ** *** ********.

** **** ***** ***** ****** ****** *** ******, **** ** stadiums, ***** ****** *** ****** ** ** **** ******** *** to ***** *****.

*******, ** **** **** ***** **** ** ******* ** *****, **** are ****** ******** ** ******** ****** ****** *** ********** *** to *** ********* ***** *** ********** ******, ****** *** ********* unsuitable.

************/*************

******'* ********** ******** *** * ****** ************* ******, **** **** one ******** *******: ***********, *********** ** *** *****. **** ****** also ***** **** **** ***** ******** ** ***** ******:

  1. ***** ***** ********:*** *** ***** ***** ***** ********, **** *** ****** ***** displayed ** *****, ******* ** ****** **** ***** *** ********* threshold, ** ****** **** ********, *** ******* *** **** ********** is ********. ***** ********** ** ******, *** ********** **** ******* from ***** ** ***** ***.
  2. ***** ***********: *** ****** ***** ******** ********* ********, **** ****** ******* frequencies ********* ** *** *** **** ******, ****** *** ***, and **** *** ***.
  3. **************: *******, ** *** ******, ******** ************** ** *****. ****** ***** from ***** (********** ***** ****) ** **** (************), **** ** green *** ***-******** ***** ******, *** ******/******/*** *** ********** ****** of ******/**********.

** ******** ********* ********** *********** *** ********* *********** **** *** course ** ******** **** ** ***** ** ******** ***** ***** ******/****** activations. *********** ******** **** **** **** ********* ** *** ********** used, **** ******** *******, *** ********** ***** ******* ** *** time ** ***********.

***** **** ***** ********, ***** ****** ****** **** *** ***** settings. ** ****** ***** ******* ** **** ******, ********* *** specific ***********, ** *** ***** ************ *****.

Video ***********

*** ***** ***** ******* ************ *** ************* ** **** ******, including *********** ********, *** *****, *** ****:


*** ***********

******'* ********* *** *** ********* **** *** ** *** ***** tested: ********, *******, *****, *** ********. ******* ** ***** **** applications, **** *** ** **** ** ******* *** ************* ** relay ******* ** *** ******, ***** *** ** ******** ********** to *** ***.

** ***** ******* *** *** *********, ***** *** **** ******* email/SMS ******** *** ******.

Audio ******** ********

*** ******** ***** **** ******** ******** ** ******* ************, **** live *** **** ******** *****.

**** **** ****** ********** ***** *** ** **** *** ************* ********, as *** ********* ******** ** *** ********* ********** *** ******** playing *** **** **** *** ******* *** *** ****** ********* performance. However, ** **** ***** *** ***** ******** ****** ** * way ** ********** **** *** ******* ** ******** *******.

**** ***** *** *****

*****, **** ******* ***** ******** ** * ***** **** * crowd ** **********. ****** ****** *** ****, ***** ** *** large ******* ** ****** ** *** ******** ****** *** *** frequencies ***** ** *** ***********. ********** ****** **** ********, *** not ******** ** **** *******:

****, ***-********** ******

****, **** ******* ***** ****, *** *** ********** ******. **** that ******** ****** **** **********, ** *** ******** ****** ***** all ******. *******, ******* ********* ******, *** ****** ** *** analyzed ** ********.

******* ***** *****

*******, **** ******* ***** ******* ***** ***** ** *** ***********. Even **** ******* ****** *** ******* ***********, ****** *** ****** constant:

Test **********

**** *** ********* ***** ** **** ***** **** ****** ******** A *** *** **-* ***** *******.

*** ********* ********/******** ******** **** **** ** **** ****:

  • ******/***** ************ ********** ********: *.*.*-******
  • **** *****: *.**.*.*
  • ***********: *.*.*.*****
  • ******* ******** ******: *.*.****.**
  • ********* ********: **** (*.**)

Comments (8)

Nice thorough review!

Couple questions,

Are those timelines stored somewhere, or once they move off the screen are they gone?

Did you play back the clips thru speakers into the room and bring it thru the back thru the Mic, or just bring the clips straight in thru the line level input?

Considering that broadcast audio normally has its noise floor ducked and frequency response tuned for speech, if you brought it in direct it would, IMHO, perform far better than one could expect in the real world.

I remember a while back reading that the Sound Intelligence could detect swearing. Is that part of this product? If so is it region specific, as colorful speech often has it localized variants.

Finally, you say that there were no false positives in the three days of open office deployment. But were there any false negatives? I know that when I'm troubleshooting a particularly uncooperative camera, I occasionally might indicate my dissatisfaction by sharing an expletive with the device. In rare cases I have even gone so far as to threaten components with a hot soldering iron.

So I guess I'm asking is, did you get a chance to yell in an aggressive manner, for whatever reason, and did it seem to trigger correctly?

Thanks!

The timeline images are not stored, but you can record the audio that preceded and followed an alarm.

The analytic is designed to use unfiltered audio streams and compression algorithms that don't filter out certain frequencies. So playing an mp3 over a speaker might work to trigger a detection, but isn't as ideal as a couple guys yelling at each other.

Swearing detection is an interesting idea. Certainly if you screamed a swear word you'd get a detection, but that's because of a stressed voice and not the word identification. So as long as people aren't softly whispering swear words at each other you'd still get a detection regardless of language being spoken.

I'd be curious to see if they soon further develop additional audio analytics includes keyword recognition, alerting and searching.

Does this product assume that audio is actually recorded or is it just for live monitoring? In some states audio can't be recorded legally without consent from both parties.

Louroe says: "The analytic isn't listening to words or languages but rather vocal stress and the associated change in frequencies."

That would help reduce the risk / concern. The analytic also does not record audio.

Ultimately, it is a legal issue but it does seem technically different than audio recording.

A novel use of this product would be to trigger the recording of audio only after and during detection, as such speech would not be considered interception of a private conversation, and would allow the capture of important audio details.

Thanks for the review. Regardless of test results, it is an innovative product from Louroe! You say you used an Axis Q1615 in the tests, but I don't understand where you're using the camera? Do you mean that you're just using the Q1615's audio feature?

Matt, the audio analytics app is running on the Axis camera and the mic is connected to the Axis camera. This is shown in the config video, which I've copied below:

Login to read this IPVM report.
Why do I need to log in?
IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

Related Reports

ONVIF Favorability Results 2019 on Mar 15, 2019
In the past decade, ONVIF has grown from a reaction to the outside Cisco-lead PSIA challenge, to being the de facto video surveillance standard...
City Physical Security Manager Interview on Mar 14, 2019
This physical security pro is the Physical Security Manager for the City of Calgary. He is a criminologist by training with an ASIS CPP credential....
Pelco GFC 4K Dome Camera Tested (IMP831-1ERS) on Mar 12, 2019
Pelco has finally released their first 4K IP camera, after years of competitors' releases. Is this move too late? Or is their new GFC Professional...
Network Optix Favorability Results 2019 on Mar 11, 2019
Network Optix is arguably the last new VMS. Founded in 2010, more than a decade after most client/server VMS offerings, the company has become a...
BCDVideo Expansion And Switch From HP To Dell Examined on Mar 11, 2019
BCDVideo says they have more than tripled revenue in the past 5 years and are continuing to grow, powered most recently by switching their lead...
Arcules Favorability Report on Mar 08, 2019
Arcules has amazing advantages. Tens of millions of funding from Canon. Unlimited access to Milestone's source code (see our test results). But...
Church Technology Director Security Interview on Mar 07, 2019
With 40+ years of experience in IT from a wide array of verticals, including US and foreign military, and large corporate and industrial settings,...
Genetec Declares "Lead With Synergis" Access Control on Mar 04, 2019
Genetec started with and is best known for its video management software. However, the company is now imploring its partners to lead with Synergis,...
Police Department Surveillance Manager Interview on Feb 28, 2019
Former Memphis PD Surveillance Manager, Lt. Joseph Patty retired months ago, but kept busy during his decades on the force, working to build up...
Salient CompleteView 20/20 VMS Tested on Feb 27, 2019
In IPVM's last test of Salient 3 years ago, we found various problems and deficiencies. Now, Salient says their new CompleteView 20/20 "unified...

Most Recent Industry Reports

Retired Mercury President Returns As Open Options President on Mar 18, 2019
Open Options experienced major changes in 2018, including being acquired by ACRE and losing its President and General Manager, John Berman who...
Large US University End-User Video Surveillance Interview on Mar 18, 2019
Schools have become targets in modern days of active shooters and terrorist fears. The need for video and access security is high. Universities...
Hikvision Favorability Results 2019 on Mar 18, 2019
Hikvision favorability results declined significantly in IPVM's 2019 study of 200+ integrators. While in 2017 Hikvision's favorability was...
ONVIF Favorability Results 2019 on Mar 15, 2019
In the past decade, ONVIF has grown from a reaction to the outside Cisco-lead PSIA challenge, to being the de facto video surveillance standard...
Hanwha Aerospace / Techwin Korean Tax Evasion Raid on Mar 15, 2019
A Hanwha group subsidiary was raided as part of a tax evasion probe. While a Korean news media report listed the raided entity as 'Hanwha...
Installation Course - Last Chance on Mar 14, 2019
This is the last chance to register for the March Installation course. This is a unique installation course in a market where little practical...
City Physical Security Manager Interview on Mar 14, 2019
This physical security pro is the Physical Security Manager for the City of Calgary. He is a criminologist by training with an ASIS CPP credential....
US Drafting Separate Rule for NDAA Dahua/Hikvision 'Blacklist' on Mar 14, 2019
The most debated provision of the NDAA ban of Dahua, Hikvision, Huawei, et al. is the so-called 'blacklist' provision which would ban any company...
OpenALPR Acquired By Mysterious Novume on Mar 13, 2019
Startup OpenALPR has been acquired by Novume, a company virtually unknown in the industry. While there are many LPR providers (see our directory),...
Milestone Machine Learning Camera Auto-Setting Examined on Mar 13, 2019
Milestone wants to improve image quality using Machine Learning to solve the problem of "a camera doesn't know what it is being used for",...

The world's leading video surveillance information source, IPVM provides the best reporting, testing and training for 10,000+ members globally. Dedicated to independent and objective information, we uniquely refuse any and all advertisements, sponsorship and consulting from manufacturers.

About | FAQ | Contact