Recording audio

Hi everyone ,

New user here and I searched this board for information about recording audio samples related to building a dataset.

Goal for my first project is to recognize the word ’ help ’ when my old mother falls on the floor of her appartment and then trigger some wireless alarm.
I’m expecting to need multiple mic’s/devices listening in different rooms, maybe some kind of mesh set up.

If I use a recorder (like the tascam-dr40x) to record audio samples from her appartment (like background noise) and her saying the word ’ help ’ in different situations (loud / soft / far away / close / tv on / shower ect) and later use a different quality mic on a mcu board… will this work ?

what would be the best way going forward ?

Hi @BoRRoZ, welcome! (I think I remember your username from the TTN forums by the way :slight_smile: ).

Yes, the normalization step that happens in the signal processing pipeline will normalize most of this (here’s some background), just make sure that you use a microphone on the MCU with proper gain, because loudness can make a difference (or do another normalization step beforehand).

Regarding “help” - this might not be an ideal word due to a high number of false positives. Something with more syllables (“BoRRoZ help”) would be more reliable.


Hi Jan tnx, yes that’s me.

OK so in an optimal situation you should record the trigger words with the same type of mic used on the MCU board ?
The problem I forsee is that the quality of these mics are bad in comparison to the devices used for recording.

Well… I don’t know if I can learn my old mother other trigger words then ‘help help’ :slight_smile:

anyway… I hope to learn and build a lot with these new techniques


So audio data typically normalizes well between microphones, I do most of my recording on mobile phone then deploy to device. But test it early.

guess have to dip my toes in the water then… tnx


It’s Kingsday in the netherlands… a good moment to continue my ‘fight’ installing CLI under win 10 :sweat_smile:


help please :scream: I’m stuck

I try to install CLI on WIN 10 pro

npm installed
node.js installed
disabled firewall when starting

and everytime stuck at the same point ''this lib is no longer supported ’
any tips :innocent:

Hi @BoRRoZ,

Those are just warnings about deprecated packages, your CLI should be installed based on your logs.
Can you run edge-impulse-daemon in the terminal?


Hi Aurelien

my mistake… it just seems to work :sweat_smile:

tnx !

1 Like

Sun is shining
Software’s working
Hardware arrived



I will try it on this one


@BoRRoZ Awesome, looking forward to see some TTN+Edge Impulse magic!

1 Like

still working on the toolchain… hard and soft

mounting OpenMV Cam H7 + on a desktop suspension scissor mic boom arm :sunglasses:


Adjustable Mic / Cam Stand

safety first :crazy_face:


Hi BoRRoz cool project, what results did you get with using training samples from the audio recorder and then running on a different device?

Hi Pete , actually, I didn’t even started (except buying some stuff) :cowboy_hat_face:

Busy finishing my new workshop and another project, and mainly, catching up reading.
I have many ideas using this new technology, So after the summer … yeah !

(I’m very curious about power consumption for example)

btw …compliments for the edge impulse FB page maintainers… always very interesting articles !

1 Like