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!

discussion

Renaming files with incorrect timestamps

Hi!I deployed passive acoustic recorders to detect animal calls but on one of my devices the date & time settings got messed up and reverted to the default (Jan 1, 2000). And...

5 1

Hi Carly,

has your issue been resolved yet? Could you link the stackoverflow question maybe? Otherwise this seems like a few lines of python code may solve this. I could assist with this if required.

R is usually not the obvious choice for file level operations :)

I don't know if this was resolved, but if you copy this code into a python file in the same folder as your .wav files and then run it, it should rename everything. Try testing it on a copy first in case something is off! This assumes that all devices are named "swift1" and all .wav files are in the same folder.

---------------------------------------------------------------------------------------------

#Reset timestamps for passive acoustic recorders

import os

from datetime import datetime,timedelta

from time import strftime

#Set Path to where you placed this file - Should be placed in folder with all recordings

os.chdir(os.path.dirname(os.path.abspath(__file__)))

#Start Date YYYY-MONTH-DAY and Time HR:MIN:SEC

start_date = "2022-06-17"

start_time= "T09:30:00"

curr_time = start_date+start_time

time = datetime.fromisoformat(curr_time)

incby = timedelta(minutes=20)

#For all .wav files in folder, set name to updated YYYYMMDD_HHMMSS and the increment by 20 minutes.

for file in os.listdir():

    tnameform = "swift1_"+time.strftime("%Y%m%d_%H%M%S.wav")

    if file[-4:] == ".wav":

        os.rename(file,tnameform)

    time = time + incby

See full post
discussion

Bioacoustic Stack Exchange

I put this out on twitter (@etgriffonage), and it was suggested that this forum would be a great feedback resource! There was a failed push 2 yrs ago to create a Bioacoustics...

3 0

I'm not a bioacoustics person but StackExchange has taught me more than half of what I know about GIS as a professional. I still regularly use and recommend it to people wanting to improve their skills at any level. Perhaps there needs to be more awareness raising amongst the bioacoustics community (as you are doing here!) about just how useful it can be, to build up the critical mass. Sadly I don't have 200 points to throw behind this, but I'll look out for anyone who does and might be tempted. Good luck!

Were you ever able to get a Bioacoustics StackExchange off the ground?  An annual retry? :)

Hi just bringing this thread back up to attention: the bioacoustics stackexchange is now up and running in beta form, and could use as much participation as possible to ensure its establishment as a community. bioacoustics.stackexchange.com

If anyone is interested in getting in and can't get an invite, please feel free to DM me and I'll pass one along.

See full post
discussion

1.5 TB micro SD

Now let us use this monster 1.5 TB microSD Card with our audiomoth ;-) ...

5 0

If only I didn't work in rainforests where canopies preclude solar panels.... *sigh* lol

Went down a rabbit hole reading the battery threads on here. It strikes me that gravity batteries might be a good solution in rainforests. String a line over the highest branch you can and then raise as much weight as you can. I'm unfamiliar with the power requirements of camera traps / audiomoths but I might do some napkin calcs if i'm bored this week. @carlybatist 

Hmm 20kg raised 5m would only buy you less than half an AA battery assuming 100% efficiency. Lame, so much for that idea.

See full post
discussion

Acoustic multilateration for gibbons

We're in the process of adjusting our acoustic multilateration (passive localisation) from working on wolves, to working on gibbons. We've been helping FFI monitor the critically...

1 1

Awesome stuff!! Interested in what kind of recorders you are using and how are you sync'ing them for the TDOA?

See full post
article

New papers on passive acoustic monitoring

PAM & transfer learning, defining occupancy in surveys, effects of anthropogenic noise on fish, soundscapes to track ecosystem recovery, detecting sharks with echosounders, using PAMGuard to detect marine mammals 

2
See full post
discussion

Sensor availability in the PRC

My lab has a visiting scholar from China who's interested in potentially conducting acoustic monitoring work once he returns home next year. It seems like most of the major...

5 0

Hi David,

I can build him one per requirements.  I'm getting started on the solar powered variant.  If your scholar is in the Beijing area, I can put him in touch with a colleague who does this sort of work.

Jamie's tip piqued my curiosity, so I bought what I thought might be what Jamie was talking about.  It is an SK-001 as detailed here (not my video) for SGD4 or thereabouts.  The price alone boggles the mind, though there are some characteristics that should be borne in mind if used for conservation work.

Foremost is the use of MP3 rather than raw uncompressed WAV which make comparing this data with existing recordings challenging.  Second, an electret condenser mic is used, so manual calibration of recordings may be required  (MEMS mics OTOH have stricter characteristics that are documented).  Third, it is unknown what kind of AGC or signal companding is used (this is in addition to data compression).   Since the device is advertised as a voice recorder, the presence of AGC/companding/noise gate features would not be surprising.  Also, I could not get it to work with a 64G micro SD card, but 32G was ok.

The SK-001 device could be useful for presence/absence type of PAM.  For other work, more testing would be needed to see if this device would be suitable.

Once again, I'm referring only to the SK-001 that I bought that I thought Jamie might be referring to.  These comments may not apply to other low cost recorders.

See full post
discussion

Careers in Bioacoustics

I'm a PhD student studying whale acoustics and am beginning to plan for the next step of my career after graduating. As a student I've met a lot of people who went on to academic...

1 0

Hi Eric, 

Dropping in a reply we had over on Linkedin here. Annoyingly I can't do a snazzy embed of the comment - will fix that!

Anton Baotic shared: 

I guess it depends on whether you want to stay in academia or go into industry. Overtime working hours are preprogrammed in academia without appropriate compensation. Austrian funding agencies pay a reasonable wage. I believe it could be improved.
I've always enjoyed working with exotic animals like elephants, giraffes, and giant pandas, as well as the collaborative and international work. This experience shaped me into the person I am today, and I don't want to missany of it. Personally, I believe that bioacoustics has not received the respect that it deserves, including the bioacousticians who put their lives into their projects. I am convinced that bioacoustics can be a valuable tool in conservation. Throughout my career, non-academics and the tech industry have approached me numerous times about using bioacoustics as a conservation monitoring tool. And I frequently feel stepped on when asked to provide material without appreciating the work behind the data, especially when it comes from economically-driven institutes that are unwilling to compensate. The fact is that the best conservation Technology is meaningless without solid basic data.
In retrospective, a more tech-oriented educational background would have been good!

Steph

See full post
discussion

Bird Acoustic Solution 

Hello Folks, I work with the Dept of Conservation, New Zealand (NZ) government. We are eagerly looking for a Machine learning or AI solution to identify the NZ birds (and...

4 0

There are a bunch of different options for detecting calls in audio data, from proper statistical platforms such as R/Python, to bespoke software such as Arbimon, Kaleidoscope & Raven. Edge Impulse also an online ML model-building interface, but this is more focused on then deploying the models onto devices for edge computing. Arbimon has template matching features that are a good way to start finding detections to build a training dataset, I have used it for this in the past. Arbimon is online & free. Kaleidoscope has a clustering function which is again a good first step to start picking out the low-hanging fruit of detections so to speak. It's a desktop app, but this is not free ($400/yr). Raven also has some automated features -  template & band-limited entropy detectors. It's also a desktop app and not free ($100-$800 depending on 1-year or permanent license and whether non-profit or not; not sure where a government agency would fit into that). 

There is always the ubiquitous split between biologists who traditionally are taught to use R and tech/computer folks who are taught to use Python, but for ML, Python's ecosystem is really well set up. Not sure what the level of programming you/your dept has, but there are a TON of free resources online for learning it if you were interested.  

Relevant Python bioacoustics packages potentially of use - Acoustic_Indices, scikit-maad, Ketos, OpenSoundscape (as well as the obvious ML ones such as TensorFlow)

Some R packages as well -  soundecology, bioacoustics, monitoR, warbleR, gibbonR

@tessa_rhinehart has created a fabulous list of bioacoustics software that you can find here: https://github.com/rhine3/bioacoustics-software

You can also turn to articles that have already done similar things and reach out to the authors to discuss their methods. I've got a (totally un-exhaustive) list of papers on passive acoustic monitoring, with a section on 'analyses' that you might find useful to start with; I can email it to you if you'd like. Working on a PAM training materials page on my website that it will be available at shortly as well (will post the link to Wildlabs when it's live!).

Hope this is helpful!  

Hi, 

Look at this publication (below) and download the BirdNet app. The computer code is provided to train ML algorithm that will allow  you to tailor the model with your own data. 

 

Thanks, Mrigesh 

 

Thank you @carlybatist , @Freaklabs and @MK . The inputs are very useful and I am progressing on my project based on that. Appreciate a lot. 

 

See full post
article

Bird Sounds Global web portal

A new web portal for annotating bird sounds has been opened called Bird Sounds Global (BSG). It is part of project LIFEPLAN, and its key objective is to develop global, automated software for bird sound identification.

2 2
Really cool platform! Will definitely add it to our next update of the Conservation Tech Directory. Curious, could there be cross-platform integration with something like Xeno-...
See full post
article

New papers on passive acoustic monitoring

Couple of hot-off-the-press papers on different passive acoustic monitoring studies, including ones on manatees, coral reef fishes, woodpeckers, insects, and using ecoacoustic indices in marine soundscapes

2 1
Another one I just came across -"Temporal separation of whale vocalizations from background oceanic noise using a power calculation"...
Another one - "Automatic acoustic heterogeneity identification in transformed landscapes from Colombian tropical dry forests" ...
See full post
discussion

Microphone for bird monitoring on Raspberry Pi

Hi, I am building a system to monitor birds (i.e. ~50-20k Hz) using a Raspberry Pi and I am looking for the best option for the microphone. I am considering: - a USB...

7 0

I can understand the reluctance to go down the I2c route on linux, but I bought some Adafruit MEMs mics (https://www.adafruit.com/product/3421) and they work fine.

If you want to dip a toe in the water, are not too cost concious, but want something you just plug in and it (largely) pretty much works, then I'd recommend looking at the seeed respeaker. Its an array, and is probably overkill for what you want. It does come with quite a bit of hand holding though, I got a "4 mic linear". Connect some jumper wires, screw on a board, install some software (!). OK for a POC (proof of concept) and as a sanity check.

Going back to the Adafruits mems breakouts, I have them wired back to the pi by re-using old CAT5 network cable, so the pi can be in one place and the mics somewhat remote - eg round the other side of a tree?  I configured a lot of software to get this working as I wanted, but it essentially removes "white noise", does file compression etc.   

apologies - ignore this reply (or if someone can delete it please do!) I have forum blindness and thought this thread was also about using Birdnet but I realise it isn't.... I suspect this is a setting on Birdnet-Pi so will post on their forums... 

Hi Paul, have been trying to get a i2c mic working with Birdnet but am having challenges in getting it working. I can install the adafruit mems you mention above and getting it working directly but when I try to use it through Birdnet I am failing. Have done some rebooting, testing, search forums but am drawing a blank - did yours work "out the box"? 

Hi Julien,
I use this mic for my raspberry pi setup and it works well picking up bird species singing in our garden while the mic and raspberry sit under our roof tiles.
Greetings,
Robin

See full post