Group

Acoustic Monitoring / Feed

Bioacoustic monitoring is one of our biggest and most active groups, with members collecting and analysing acoustic data from every type of wildlife, from birds and bats to big cats, and even reptiles!

article

RSEC Journal: Ecoacoustics and Biodiversity Monitoring

Remote Sensing in Ecology & Conservation
The Acoustic Monitoring community is one of the most active spaces on WILDLABS, and this particular aspect of conservation technology is rapidly growing, offering new ways to answer large-scale environmental questions...

0
See full post
discussion

Looking for a collaborator with CNN/app development experience

Hi all! I am looking to collaborate with someone with expertise in building CNNs and developing smartphone apps on an acoustic monitoring & citizen science project...

2 0

Hi Sophia, 

Just wondering what 'collaborate' means here - are you looking for a volunteer on the project or do you have budget to support the project? 

Steph  

Hi Steph! It could be either - if there was anyone out there for whom this work would be a good fit for their current role, then that would be easy, but if they needed their time paying for then I have extra funds I can apply for, which I would feel fairly confident about.

See full post
discussion

Distinguishing Noise from Sounds - a question of recognition?

Hi there, Does anyone know of anyone researching into the identification of different noises, as opposed to distinct sounds, and can they point me at them please? By "...

4 0

Thanks Nick,

In discussion here this issue of unknown classifications may be a widespread problem for supervised learning models? A colleague PhD candidate here is working on sound classification and mentioned the self same problem today. For example, "Cat", "Dog", "Everything else"? Is the "Everything else" state space (much) bigger than the two classifying state spaces?

One suggestion has been to take very small slices of "Squawk" of the flock of birds and use a distinct slice of frequencies from the spectrum thereof?

A problem remains however: how distinct is the combined squawk of a Quelea bird from other flocks of small birds?

Any advice on how to build specific classifiers would be most helpful?

Many thanks,

Andrew.

It sounds like you are referring to what is often called the "Cocktail Party" problem.  There has been quite a bit of research in this area, but it is a very hard problem.  I would start with the general literature on this topic as there isn't much in the conservation space. Check the hearing aid literature....picking out someone talking in a crowd of voices and sounds.  Humans are pretty amazing at this...machines not so much.  You might consider following up on some recent research at MIT:

https://blogs.nvidia.com/blog/2018/08/28/music-youtube-cocktail-party-problem-ai-artificial-intelligence-deep-learning/

For what its worth, it's a fascinating problem and has a lot of conservation applications.  As Nick mentioned, the biggest challenge is getting enough usable soundscapes.

Hi cosmicspittle,

 

Many thanks for the pointer, I shall discusss it with our local tech disussion group here tomorrow morning. One of the guy's, the PhD candidate in tehrapy audio analysis, will be most ineterested as well. Our project is indeed becoming ever more interesting, like an onion, peeling away layers of complexity. The key difference using our DSP methodology is that the spctrum has few if any harmonic cycles to identify, being of a low deviation level at a thin range of dB acros sht ewhole specturm. Thus each frequeny is much like th elast, giving no pattern to cross-correlate. At this stage we do not think machine learning will give us much either without some way of getting a pattern to match somewhere? One suggestion has been to take a series of very thin slices of frequencies when we know the squeak occurs using audacity as our source range, but as I say, the y-xis dB for every frequncy deviates very little, hence it is just "squelch"?

 

I hope to gain something from the research you mention, many thanks.

All the best,

Andrew.

See full post
event

Training Opportunity: HarvardX TinyML Course

edX
Want to build your professional skills in TinyML? Harvard University and Google TensorFlow are offering a new online Professional Certificate program of 3 skill-building courses, designed to cover the essential "...

0
See full post
event

Webinar: Advances in Fisheries Electronic Monitoring

SAFET
2020 Seafood and Fisheries Emerging Technology Conference kicks off their webinar series this Thursday, Sept. 24th at 5 PM PT/ 8 PM ET. Register now for New Models, New Applications: Advances in Fisheries Electronic...

0
See full post
article

Meet the Scientists of Black Mammalogists Week!

Black Mammalogists Week
To celebrate the first Black Mammalogists Week (starting Sunday, September 13th), we talked to four of the amazing Black scientists behind this event! Find out what they had to say about their favorite (and most...

0
See full post
event

Tech Tutors: Review Session

WILDLABS Team
Missing Tech Tutors? Us too! Catch up on every episode from Season 1, check out some of our community highlights, and find out what we loved most about launching this series in this mid-week Tech Tutors review session....

0
See full post
event

African Bioacoustics Community Conference

African Bioacoustics Community Conference
Registration is now open to attend this year's virtual African Bioacoustics Community Conference, taking place November 2nd - 5th! Created to provide a networking forum for people working on all aspects of bioacoustic...

0
See full post
article

Sustainable Fishing Challenges: Fishing Gear Innovations

Daniel Steadman
Today, Sustainable Fishing Challenges group leader Daniel Steadman discusses how fishing gear itself could benefit from fresh technological innovations to prevent both environmental damage and damage to species and...

0
See full post
funding

Challenge: ElephantEdge

hackster.io
Protecting elephants from conservation's most pressing issues like poaching and human-wildlife conflict requires big, bold, and innovative solutions. Hackster.io, Smart Parks, Edge Impulse, Microsoft, and several other...

0
See full post
discussion

AudioMoth Water Resistant Case Design

Hi,    I’d like to share a low cost design for water resistant cases for AudioMoths that I created (instructions in the attached image). I’d say...

7 0

Hi, do you still have some left overs of hyrdrophobic cloth? I'm currently in Mexico but a friend of mine is in UK so she can bring them to me. Thank you so much. 

Hi - I'm down to three sheets - the usable area is 12cm by 12 cm - I did post some cloth to the US and the total  price was under $5USD which I think would be 80-100 Peso but equally happy to send to your friend.  Email me b[email protected] and we can sort out fine details - one thing is I'm away from home till early september. so couldn't send till then and the UK-Mexico post take about 5 days.  Best Wishes -  David Brown

Hello to you all, I hope everyone is doing ok during this Covid-19 contingency.

Jsut sharing this adaptation for the water proof case for the Audio Moth.

https://www.tetrixecology.com/single-post/Developing-an-Enclosure-for-the-AudioMoth-Acoustic-Logger---Part-1

See full post
event

How do I build bespoke conservation technology?

Nigel Butcher
Our sixth WILDLABS Tech Tutor is Nigel Butcher, who tackled the question: How do I build bespoke conservation technology? What are the key things I should think about/look out for? You can catch up on this tutorial on...

0
See full post
discussion

Help with analysing bat recordings from Audiomoth

Hi  I was hoping someone could point me in the right direction. First time poster....... I’m very much an enthusiastic amateur who is trying to improve the...

5 0

Hi Carlos 

Thank you for your message. I would quite like to send you some files. What's the best email address to send them to? 

Thanks 

Johnnie 

See full post
discussion

Tech Tutors: How do I scale up acoustic surveys with Audiomoths and automated processing?

Hi Wildlabbers,  It's almost time for our fourth Tech Tutors session tomorrow with Tessa Rhinehart, who will be tackling the question: How do I scale up...

1 0

Hi everyone,

Thanks for attending today's episode! You can find all of the collaborative notes at the link below, and we also encourage you to use this thread to connect and collaborate with the people you met in the chat.

https://notes.datawrapper.de/p/Tech_Tutors_Episode_4

We'll be posting the video and slides here tomorrow.

And as always, please use this thread to ask any follow-up questions you have for Tessa and the acoustic monitoring community!

-Ellie

See full post
discussion

Tech Tutors: How do I perform automated recordings of bird assemblages?

Hi Wildlabbers,  It's almost time for our third Tech Tutors session tomorrow with Carlos Abrahams, who will be tackling the question: ...

1 0

Hi everyone,

If anyone is looking for the episode's collaborative notes, you can find them here:

https://notes.datawrapper.de/p/Tech_Tutors_Episode_3

This doc features all the questions asked in this episode, as well as additional resources, participant introductions, and other helpful links.

-Ellie

See full post
funding

Competition: Cornell Birdcall Identification

The Cornell Lab of Ornithology
Put your acoustic monitoring skills to the test in The Cornell Lab of Ornithology's Birdsong Identification Kaggle Competition. Participants will compete to identify as many bird vocalizations as possible in in...

0
See full post
event

How do I scale up acoustic surveys with Audiomoths?

Tessa Rhinehart
Our fourth WILDLABS Tech Tutor is Tessa Rhinehart, who tackled the question: How do I scale up acoustic surveys with Audiomoths and automated processing? You can catch up on this tutorial on our Youtube channel and read...

0
See full post
event

How do I perform automated recordings of bird assemblages?

Carlos Abrahams
Our third WILDLABS Tech Tutor is Carlos Abrahams, who tackled the question: How do I perform automated recordings of bird assemblages? You can catch up on this tutorial on our youtube channel and read through the...

0
See full post
event

How do I train my first machine learning model?

Daniel Situnayake
Our first WILDLABS Tech Tutor is Daniel Situnayake, who tackled the question: How do I train my first machine learning model?  To join one of our upcoming tutorials, visit the Tech Tutors series page. 

0
See full post
discussion

How are you using your Audiomoth?

The 'Audiomoth: Who wants to join a group buy?' case study in our Annual Report...

5 0

I'm in North Somerset UK and have two AudioMoths.  I've adapted some waterproof cases which also can be locked and strapped onto a tree etc using a python cable.  This allow me to use them safely in semi-public spaces.  My interst is surveying for bats and recording them with the land owners.  I got interested in having a recorder, when helping to trap for nathusius' pipistrelle on a site I've know for 10 years - and just because I was out later than I normally survey we found not only nathusius' pipistrelle but a passing Lesser Horseshoe on my Petterson M500usb - so I decided to get some AudioMoths and play!

My Website is here 

As well as the points highlighted by Steph, Open Acoustic Devices are also running an online survey to capture the use of AudioMoth. To evaluate the global impact of open-source conservation technology, it is important to know how the technology is being used. This survey will go towards a human-computer interaction study into the usability of tech in conservation, and also used to evaluate the global impact of open-source conservation technology. AudioMoth is being used as a case study to identify best practises for open-source conservation technology development and accessibility. 

It would be great to keep sharing your experiences on this thread and if you have time here with our online survey. 

How do we get notified for the next group buy?

See full post
discussion

standards

Hello all, I am new to recording but have been learning about acousting environmental monitoring for several years now. Covid19 has me wanting to start recording more than ever...

0
See full post
event

WILDLABS Tech Tutors: Season One

WILDLABS Team
We've wrapped season one of Tech Tutors! Thank you to all of our Tutors, and to everyone who attended and made these episodes so exciting! You can find all of our episodes on the WILDLABS Youtube Channel, and find...

0
See full post
discussion

Audiograms- the range species can hear at

We are conducting a study looking for the auditory range of different species - the range at which they can sound. We have only found one authoritative source - ...

2 0

I'm a primatologist so can't say too much about other mammal taxa, but I believe this is the most comprehensive resource for primate audiograms--

Coleman, M. N. (2009). What do primates hear? A meta-analysis of all known nonhuman primate behavioral audiograms. International Journal of Primatology, 30(1), 55-91.

Hi Isla,

Range at which animals hear sounds depend on 4 things:

1) the frequency (pitch) of the sound of interest. As a rule of thumb, lower frequency sounds travel farther since high frequency sounds are subject to more absorption transmission losses.

2) the medium in which the sound is being transmitted in (i.e. sound travels at ~1500m/s in seawater and ~340m/s in air).

3) the audiogram of the animal (i.e. what frequencies CAN they hear), which Carly is referring to in the previous comment. 

There has been a lot of audiogram research on marine mammals. Find an overview and links to a handful of publications here: https://dosits.org/animals/effects-of-sound/measure-marine-mammals-reaction-to-sound/hearing-sensitivity-studies/ . This has also recently been explored in diving seabirds from SDU (university of southern denmark).

and 

4) the noise levels in the environment, as sounds can only be distinguished if they have some decent signal-to-noise ratio.

If you have any specific more questions, get in touch.

Cheers,

Chloe 

See full post
discussion

Any here used Cornell's Swift Recorder?

Hi everyone If you've used Cornell's Swift Recorder, I'd love to chat. In particular, I'm interested to hear people's experiences with battery life. It'...

4 0

Hi Daniella,

Yes, I have used SWIFT, SongMeter SM4, and Audiomoths. I find Swift to be the most energy efficient. They are also very affordable. Currently, they are my number one choice.  In reality, however, I would say that whether you use Swift over other sensors, particularly Audiomoths, would depend on the type of study you want to do and how often you can get to the sensors to replace batteries. Happy to talk about cons and pros if you want. Just send me an email here: [email protected]

Cheers,

David

Hello Daniella, 

We, WCS Mongolia, used lithium batteries for SWIFT recorders, the most of them still working in until now, since the last August.

At the Cornell SAW, they said alkanium battery will be working 27-44 days, and it depends on configuration sample rate.

We are configured 8K for sampling rate, and 24 hours recording.

Thanks,

Ochiroo

 

 

We used the following lithium batteries.

 

URL:

https://fortebattery.en.made-in-china.com/product/FBDEubqyfGhH/China-C-Size-Lithium-Batteries-Cr26500-Cr26500se-Er26500-Er26500m.html

See full post
discussion

Virtual Meetup Discussion: Acoustic Monitoring

Hi everyone.  We're a few hours away from our...

3 0

Hi all,

I missed this, but just watched the virtual meeting recording.  Towards the end Stephanie mentioned there were many questions about recording multiple channels for localisation.  I hadn't thought there was that much interest in it.  Anyway my collaborator/client and I have been working on this off and on and slowly, but she did present some results she got at the recent conference in NZ.  If there is any interest I'll see if I can get her to give out her slides or something.

On another tack I'm interested in the experience of anyone who has done gunshot/blast fishing localisation.  In particular I'm curious about the algo used for detection and also for localisation.  I'm taking the matched filter approach for detection but am now wondering if maybe CNN classification might be better.

Finally I'm interested if anyone has ideas about implementing a LoRa mesh, or knows of a useable mesh layer.

Thanks,

-harold 

Where would I be able to find the recording of this virtual meetup? Thanks!

See full post